CHAPTER-1

INTRODUCTION
1.1 Introduction:
With the widespread of personal mobile devices and the ubiquitous access to the
internet, the global number of digital buyers is expected to reach 2.14 billion people
within the next few years, which accounts for one fourth of the world population. With
such a huge number of buyers and the wide variety of available products, the efficiency
of an online store is measured by their ability to match the right user with the right
product, here comes the usefulness of a product recommendation systems. Generally
speaking, product recommendation systems are divided into two main classes: (1)
Collaborative filtering (CF), CF systems recommend new products to a given user based
on his/her previous (rating/viewing/buying) history Sahraoui Dhelim, Huansheng Ning
and Nyothiri Aung are with School of Computer and Communication Engineering,
University of Science and Technology Beijing, 100083, Beijing, China. Runhe Huang
and Jianhua Ma are with the Faculty of Computer and Information Sciences Hosei
University, Japan. Corresponding author: Huansheng Nin([email protected]).
Manuscript received September 24, 2019; revised October 03, 2020. and his/her
neighbours. For example, as shown in Figure 1 (a), most of the people of previously
bought a football jersey, they have also bought a football, thus the system predicate that
the user might be interested in buying a football. (2) Content filtering or content-based
filtering (CBF). CBF systems recommend new items by measuring their similarity with
the previously (rated/viewed/bought) products. For example, as shown in Figure 1 (b),
the football is recommended because semantically similar to the football jersey.

Fig.1.1: Collaborative filtering and content filtering

1
 Far from that, with the popularity of online social networks such as Facebook,
Twitter and Instagram, many users use social media to express their feeling or opinions
about different topics, or even explicitly expressing their desire to buy a specific product
in some cases. Which made social media content a rich resource to understand the users’
needs and interests [1]. On the other hand, the emerging of personality computing [2]
has offered new opportunities to improve the efficiency of user modelling in general and
particularly recommendation systems by incorporating the user’s personality traits in the
recommendation process. In this work, we propose a product recommendation system
that predicts the user’s needs and the associated items, even if his history does not
contain these items or similar ones. This is done by analyzing the user’s topical interest,
and eventually recommend the items associated with the theses interest. The proposed
system is personality-aware from two aspects; it incorporates the user’s personality
traits to predict his topics of interest, and to match the user’s personality facets with the
associated items. As shown in Figure 2 the proposed system is based on hybrid and
filtering approach (CF and CBF) personality-aware interest mining.

Fig. 1.2: Interest mining based product recommendations

Since we have multiple types of nodes (users, items and topics), the system is modelled
as a heterogeneous information network (HIN), which includes multiple types of nodes
and links. In our case, product recommendation could be formulated as link prediction
in HIN [3]. For example, in Figure 2, given the user’s previous rating and topical
interest represented in a HIN, the problem is to predict whether or not a link exists
between the user and the product (the ball). One of the main challenges of link
prediction in HIN is how to maintain a reasonable balance between the size of
information considered to make the prediction and the algorithm complexity of the

2
techniques required to collect that information. Since in practice, the networks are
usually composed out of hundreds of thousands or even millions of nodes, the method
used to perform link prediction in HIN must be highly efficient. However, computing
only local information could lead to poor predictions, especially in very sparse
networks. Therefore, in our approach, we make use of meta-paths that start from user
nodes and end up in the predicted node (product nodes in our case), and try to fuse the
information from these meta-paths to make the prediction. The contributions of this
work are summarized as follows: 1) Propose a product recommendation system that
infers the user’s needs based on her/his topical interests. 2) The proposed system
incorporates the user’s Big-Five personality traits to enhance the interest mining
process, as well as to perform personality-aware product filtering. 3) The relationship
between the users and products is predicted using a graph-based meta path discovery,
therefore the system can predict implicit as well as explicit interests. The remainder of
this paper is organized as follows. In Section 2 we review the related works, while in
Section 3 the system design of the proposed system is presented. In Section 4 we
evaluate the proposed system. Finally, in Section 5 we conclude the work and state
some of the future directions.
1.2 Scope:
The scope of our Personality-Aware Product Recommendation System spans the
intersection of user psychology, interest mining, and metapath discovery. We aim to
analyze user preferences, behaviours, and interactions to unearth valuable insights into
individual personalities. By employing advanced algorithms for metapath discovery, we
connect the dots between diverse product categories, ensuring holistic and context-
aware recommendations. The system's scope encompasses not just product suggestions,
but a comprehensive understanding of users' evolving tastes, ultimately shaping a
dynamic and highly personalized shopping journey.

1.3 Purpose:

The purpose of our Personality-Aware Product Recommendation System is to

revolutionize the online shopping experience. By leveraging user interest mining and
metapath discovery, our system aims to achieve the following:

3
1.3.1 Personalization:

Tailor recommendations based on users' unique personalities and evolving

interests, ensuring a more engaging and relevant shopping experience.

1.3.2 Enhanced User Understanding:

Gain deeper insights into user preferences, behaviours, and connections between
different product categories through metapath discovery, allowing for a comprehensive
understanding of individual tastes.

1.3.3 Dynamic Adaptability:

Continuously adapt to users changing preferences by employing advanced

algorithms that analyse metapaths, ensuring recommendations stay relevant over time.

1.3.4 Improved Engagement:

Foster increased user engagement and satisfaction by offering personalized

suggestions that align not only with explicit preferences but also with the subtleties of
individual personalities.

1.3.5 Cross-Category Recommendations:

Explore connections between seemingly disparate product categories, providing

users with serendipitous discoveries and expanding their shopping horizons.

In essence, our system aspires to redefine how users discover and interact with
products, making the online shopping experience not just efficient but an enjoyable
journey reflective of their unique tastes and personalities.

1.4 Objective:

The primary objectives of our Personality-Aware Product Recommendation

System, driven by user interest mining and metapath discovery, include:

Precision in Recommendations: Develop algorithms that accurately mine user

interests and preferences, ensuring precise and relevant product recommendations
tailored to individual personalities.

4
1.4.1 Dynamic User Profiling:

Implement a robust system for continuously updating and refining user profiles,
incorporating real-time changes in preferences through effective metapath discovery.

1.4.2 Enhanced User Experience:

Elevate the overall shopping experience by providing users with

recommendations that not only align with their explicit preferences but also consider
subtle nuances in their personalities, fostering a deeper connection.

1.4.3 Adaptability and Evolution:

Build a system that adapts to evolving user preferences over time, utilizing
metapath discovery to understand the evolving relationships between different product
categories and user interests.

1.4.4 Interdisciplinary Connections:

Explore metapaths to identify connections between diverse product categories,

offering users serendipitous and cross-category recommendations that go beyond
traditional silos.

1.4.5 User Engagement:

Increase user engagement by delivering recommendations that capture user

attention, leading to a more satisfying and enjoyable shopping journey.

1.4.6 Algorithmic Transparency:

Ensure transparency in the recommendation process, allowing users to

understand how their preferences are analysed and how recommendations are generated
based on metapath discovery and interest mining.

By focusing on these objectives, our system aims to create a transformative and

highly personalized online shopping environment that caters to the unique personalities
and evolving preferences of each user.

5
 CHAPTER-2

LITERATURE SURVEY

In this section, we review the recent advances of personality aware

recommendation system and interest mining schemes as well. A. Personality and
recommendation systems Many works have discussed the importance of incorporating
the user’s personality traits in the recommendation systems. Yang et al. [4] proposed a
recommendation system of computer games to players based on their personality traits.
They have applied text mining techniques to measure the players’ Big-five personality
traits, and classified a list of games according to their matching with each dominant
trait. They have tested their proposed system on 2050 games and 63 players form Steam
gaming network. While Wu et al. [5] presented a personality based greedy re-ranking
algorithm that generates the recommended list, where the personality is used to estimate
the users’ diversity preferences. Ning et al. [6] proposed a friend recommendation
system that incorporates the Big-five personality traits model and hybrid filtering,
where the friend recommended process is based on personality traits and the users’
harmony rating. Ferwerda et al. [7] studied the relationship between the user’s
personality traits and music genre preferences, they have analysed a dataset that
contains personality test scores and music listening histories of 1415 Last.fm users.
Similarly in [8] they conducted an online user survey where the participants were asked
to interact with an application named Tune-A-Find, and measured taxonomy choice (i.e.
activity, mood, or genre), individual differences (e.g. music expertise factors and
personality traits), and different user experience factors. Similarly, Hafshejani et al. [9]
proposed a collaborative filtering system that cluster the users based on their Big-Five
personality traits using K-means algorithm. Following that, the unknown ratings of the
sparse user-item matrix are estimated based on the clustered users. Dhelim et al. [10]
discussed the benefits of capturing the user’s social feature such as personality traits that
are represented as a cyber entities in the cyberspace. Similarly, Khelloufi et al. [11]
showed the advantages of leveraging the user’s social features in the context of service
recommendation in the Social Internet of Things (Slot). B. Interest mining Far from
personality, many previous works have discussed user interest mining from social media

6
content. Piao et al. [1] surveyed the literature of user interest mining from social
networks, the authors reviewed all the previous works by emphasizing the following on
four aspects, (1) data collection, (2) representation of user interest profiles, (3)
construction and refinement of user interest profiles, and (4) the evaluation measures of
the constructed profiles. Zarrinkalam et al. [12] presented a graph-based link prediction
scheme that operates over a representation model built from three categories of
information: user explicit and implicit contributions to topics, relationships between
users, and the similarity among topics. Trikha et al. [13] investigated the possibility of
predicting the users’ implicit interests based on only topic matching using frequent
pattern mining without considering the semantic similarities of the topics. While Wang
et al. [14] proposed a regularization framework based on the relation bipartite graph,
that can be constructed from any kind of relationships, they evaluated the proposed
system from social networks that were built from retweeting relationships. In [15], the
authors discussed the usage of user’s interests to customize the services offered by a
cyber-enabled smart home. Faralli et al. [16] proposed Taxionomy, a method for
modelling of Twitter users by a hierarchical representation based on their interests.
Twiconomy is built by identifying topical friends (a friend represents an interest instead
of social relationship) and associate each of these users with a page on Wikipedia.
Dhelim et al. [17] used social media analysis to extract the user’s topical interest. Kang
et al. [18] proposed a user modelling framework that maps the user’ posted content in
social media into the associated category in the news media platforms, and based on
they used Wikipedia as a knowledge base to construct a rich user profile that represents
the user’ interests. Liu et al. [19] introduced iExpand, a new collaborative filtering
recommendation system based on user interest expansion via personalized ranking.
iExpand uses a three layer, user-interests-item, representation scheme, which makes the
recommendation more accurate and with less computation cost and helps the
understanding of the interactions among users, items, and user interests. Table I shows a
comparison between the proposed system and some of the related works presented
above. Some works such as metapath2vec [20], Shi et al. [21] have used metapaths
embedding to represent the network information in lower dimensions for easy
manipulation of heterogeneous graphs. However, in highly dynamic graphs such as the
user-topic product graph in our case, where the graph update happens very frequently,

7
computing the meta-path embedding all over again is very expensive in terms of
computation.

2.1 Existing System:

Existing systems typically incorporated collaborative filtering, content based

filtering, or hybrid approaches for recommendations. Advanced systems considered user
behaviours, historical data, and preferences, but incorporating explicit personality traits
and metapath discovery was a more cutting-edge direction.

2.2 Proposed System:

In our proposed Personality-Aware Product Recommendation System, we

envision a comprehensive framework that seamlessly integrates user interest mining and
metapath discovery for a highly personalized and adaptive shopping experience:

2.2.1 User Profiling and Personality Mapping:

Develop a robust user profiling mechanism to capture explicit preferences,

purchase history, and demographic information. Incorporate personality indicators
through user surveys, psychographic data analysis, or leveraging existing behavioural
data.

2.2.2 Interest Mining Algorithms:

Implement state-of-the-art machine learning algorithms to mine implicit and

explicit user interests from diverse data sources, including browsing behaviour, search
history, and social interactions. Integrate sentiment analysis to gauge user preferences
and satisfaction levels.

2.2.3 Metapath Discovery Engine:

Design algorithms for metapath discovery that analyze intricate relationships

between different product categories. Explore semantic connections and historical
patterns to uncover meaningful metapaths, enhancing the understanding of user-product
associations.

8
2.2.4 Dynamic User Models:

Create dynamic user models that adapt to changing preferences and evolving
personalities over time. Employ metapath-based insights to continuously refine and
update user profiles, ensuring recommendations remain relevant.

2.2.5 Context-Aware Recommendation System:

Incorporate contextual awareness to consider external factors such as seasonal

trends, social influences, and emerging preferences. Implement real-time adjustments to
recommendations based on contextual information, providing timely and relevant
suggestions.

2.2.6 Explainability and Transparency Features:

Integrate features that explain the rationale behind each recommendation,

highlighting the influence of personality traits and metapath connections. Provide users
with transparency controls, allowing them to customize the level of personal
information used for recommendations.

2.2.7 User Feedback Loop:

Establish a continuous feedback loop to collect explicit feedback from users on

recommended products. Utilize feedback data to iteratively improve the
recommendation algorithms, ensuring a responsive and user-centric system.

2.2.8 Cross-Category Recommendations:

Explore and leverage metapaths to offer serendipitous cross-category

recommendations, expanding users' exploration beyond their typical preferences. By
integrating these components, our proposed system aims to create an intelligent,
adaptable, and transparent recommendation engine that not only understands users'
interests but also respects their individual personalities, providing a truly personalized
and engaging shopping experience.

2.3 Advantages of proposed system:

9
 The proposed system offers personalized product recommendations by
integrating user interest mining and metapath discovery. By analyzing individual
preferences, it tailors suggestions, enhancing user satisfaction. Metapath discovery adds
depth, identifying intricate relationships in user behaviour for more accurate predictions.

2.4 Feasibility study:

The feasibility of the project is analyzed in this phase and business proposal is
put forth with a very general plan for the project and some cost estimates. During
system analysis the feasibility study of the proposed system is to be carried out. This is
to ensure that the proposed system is not a burden to the company.
Three key considerations involved in the feasibility analysis are

2.4.1 ECONOMICAL FEASIBILITY:

This study is carried out to check the economic impact that the system will have
on the organization. The amount of fund that the company can pour into the research
and development of the system is limited. The expenditures must be justified. Thus the
developed system as well within the budget and this was achieved because most of the
technologies used are freely available. Only the customized products had to be
purchased. 2.4.2 TECHNICAL FEASIBILITY:

This study is carried out to check the technical feasibility, that is, the technical
requirements of the system. Any system developed must not have a high demand on the
available technical resources. This will lead to high demands on the available technical
resources. This will lead to high demands being placed on the client. The developed
system must have a modest requirement, as only minimal or null changes are required
for implementing this system.

2.4.3 SOCIAL FEASIBILITY:

The aspect of study is to check the level of acceptance of the system by the user.
This includes the process of training the user to use the system efficiently. The user
must not feel threatened by the system, instead must accept it as a necessity. The level
of acceptance by the users solely depends on the methods that are employed to educate
the user about the system and to make him familiar with it. His level of confidence must
be

10
raised so that he is also able to make some constructive criticism, which is welcomed, as
he is the final user of the system.

CHAPTER-3

SOSTWARE REQUIREMENTS ANALYSIS

3.1 Classification:

3.1.1 Support Vector Machine (SVM):

In classification tasks a discriminant machine learning technique aims at finding,

based on an independent and identically distributed (id) training dataset, a discriminant
function that can correctly predict labels for newly acquired instances. Unlike
generative machine learning approaches, which require computations of conditional
probability distributions, a discriminant classification function takes a data point x and
assigns it to one of the different classes that are a part of the classification task. Less
powerful than generative approaches, which are mostly used when prediction involves
outlier detection, discriminant approaches require fewer computational resources and
less training data, especially for a multidimensional feature space and when only
posterior probabilities are needed. From a geometric perspective, learning a classifier is
equivalent to finding the equation for a multidimensional surface that best separates the
different classes in the feature space.
SVM is a discriminant technique, and, because it solves the convex optimization
problem analytically, it always returns the same optimal hyperplane parameter in
contrast to genetic algorithms (GAs) or perceptron, both of which are widely used for
classification in machine learning. For perceptron, solutions are highly dependent on the
initialization and termination criteria. For a specific kernel that transforms the data from
the input space to the feature space, training returns uniquely defined SVM model
parameters for a given training set, whereas the perceptron and GA classifier models are
different each time training is initialized. The aim of GAs and perceptron is only to
minimize error during training, which will translate into several hyperplanes’ meeting
this requirement.
3.1.2 Logistic Regression:

11
 Logistic regression analysis studies the association between a categorical
dependent variable and a set of independent (explanatory) variables. The name logistic
regression is used when the dependent variable has only two values, such as 0 and 1 or
Yes and No. The name multinomial logistic regression is usually reserved for the case
when the dependent variable has three or more unique values, such as Married, Single,
Divorced, or Widowed. Although the type of data used for the dependent variable is
different from that of multiple regression, the practical use of the procedure is similar.

Logistic regression competes with discriminant analysis as a method for

analysing categorical-response variables. Many statisticians feel that logistic regression
is more versatile and better suited for modelling most situations than is discriminant
analysis. This is because logistic regression does not assume that the independent
variables are normally distributed, as discriminant analysis does.
This program computes binary logistic regression and multinomial logistic
regression on both numeric and categorical independent variables. It reports on the
regression equation as well as the goodness of fit, odds ratios, confidence limits,
likelihood, and deviance. It performs a comprehensive residual analysis including
diagnostic residual reports and plots. It can perform an independent variable subset
selection search, looking for the best regression model with the fewest independent
variables. It provides confidence intervals on predicted values and provides ROC curves
to help determine the best cutoff point for classification. It allows you to validate your
results by automatically classifying rows that are not used during the analysis.
3.1.3 Naive Bayes:

The naive bayes approach is a supervised learning method which is based on a

simplistic hypothesis: it assumes that the presence (or absence) of a particular feature of
a class is unrelated to the presence (or absence) of any other feature.
Yet, despite this, it appears robust and efficient. Its performance is comparable to
other supervised learning techniques. Various reasons have been advanced in the
literature. In this tutorial, we highlight an explanation based on the representation bias.
The naive bayes classifier is a linear classifier, as well as linear discriminant analysis,
logistic regression or linear SVM (support vector machine). The difference lies on the
method of estimating the parameters of the classifier (the learning bias).

12
 While the Naive Bayes classifier is widely used in the research world, it is not
widespread among practitioners which want to obtain usable results. On the one hand,
the researchers found especially it is very easy to program and implement it, its
parameters are easy to estimate, learning is very fast even on very large databases, its
accuracy is reasonably good in comparison to the other approaches. On the other hand,
the final users do not obtain a model easy to interpret and deploy, they do not
understand the interest of such a technique.
Thus, we introduce in a new presentation of the results of the learning process.
The classifier is easier to understand, and its deployment is also made easier. In the first
part of this tutorial, we present some theoretical aspects of the naive bayes classifier.
Then, we implement the approach on a dataset with Tanagra. We compare the obtained
results (the parameters of the model) to those obtained with other linear approaches
such as the logistic regression, the linear discriminant analysis and the linear SVM. We
note that the results are highly consistent. This largely explains the good performance of
the method in comparison to others. In the second part, we use various tools on the
same dataset (Weka 3.6.0, R 2.9.2, Knime 2.1.1, Orange 2.0b and RapidMiner 4.6.0).
We try above all to understand the obtained results.
3.2 Modules:

3.2.1 Service Provider:

In this module, the Service Provider has to login by using valid user name and
password. After login successful he can do some operations such as Train and Test Data
Sets, View Trained and Tested Accuracy in Bar Chart, View Trained and Tested
Accuracy Results, Predict Product Recommendation From Data Set Details, Find
Product Recommendation Prediction Ratio on Data Sets, Download Trained Data Sets,
View Product Recommendation Prediction Ratio Results, View All Remote Users.

3.2.2 View And Authorize users:

In this module, the admin can view the list of users who all registered. In this,
the admin can view the user’s details such as, user name, email, address and admin
authorizes the users.

3.2.3 Remote User:

13
 In this module, there are n numbers of users are present. User should register
before doing any operations. Once user registers, their details will be stored to the
database. After registration successful, he has to login by using authorized user name
and password. Once Login is successful user will do some operations like Post Product
data sets, Predict Product Recommendation, View Your Profile.

14
 CHAPTER-4

SOFTWARE DESIGN

4.1 Class Diagram:

Fig.4.1. Class Diagram

15
4.2 Sequence Diagram:

Fig.4.2.Sequence Diagram

16
4.3 Use Case Diagram:

Fig.4.3. Use Case Diagram

17
4.4 Data Flow Diagram:

Fig.4.4. Data Flow Diagram

18
4.5 Flow Charts:

4.5.1 Service Provider:

Fig.4.5. Service Provider

19
4.5.2 Remote User:

Fig.4.6. Remote User

20
 CHAPTER-5

SOFTWARE AND HARDWARE REQUIREMENTS

5.1 Software Requirements:

 Operating system : Windows 7 Ultimate
 Coding Language : Python
 Front-End : Python
 Back-End : Django-ORM
 Designing : Html, css, javascript
 Data Base : MySQL (WAMP Server)
5.2 Hardware System Configuration:

 Processor : Pentium –IV

 RAM : 4 GB (min)
 Hard Disk : 20 GB
 Key Board : Standard Windows Keyboard
 Mouse : Two or Three Button Mouse
 Monitor : SVGA

21
 CHAPTER-6

CODING

6.1 Code:

from django.db.models import Count

from django.db.models import Q
from django.shortcuts import render, redirect, get_object_or_404
import datetime
import openpyxl
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import re
from sklearn.ensemble import VotingClassifier

import warnings
warnings.filterwarnings("ignore")
plt.style.use('ggplot')
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics import accuracy_score, confusion_matrix,
classification_report
from sklearn.metrics import accuracy_score
from sklearn.metrics import f1_score

# Create your views here.

from Remote_User.models import

ClientRegister_Model,Product_Details,Recommend_Prediction,detection
_ratio,detection_accuracy

def login(request):

if request.method == "POST" and 'submit1' in request.POST:

username = request.POST.get('username')

password = request.POST.get('password')

try:

22
 enter =
ClientRegister_Model.objects.get(username=username,password=passwor
d)

request.session["userid"] = enter.id
return redirect('Add_DataSet_Details')
except:
pass

return render(request,'RUser/login.html')

def Add_DataSet_Details(request):
if "GET" == request.method:
return render(request, 'RUser/Add_DataSet_Details.html',
{})
else:
excel_file = request.FILES["excel_file"]
# you may put validations here to check extension or file
size
wb = openpyxl.load_workbook(excel_file)
# getting all sheets
sheets = wb.sheetnames
print(sheets)
# getting a particular sheet
worksheet = wb["Sheet1"]
print(worksheet)
# getting active sheet
active_sheet = wb.active
print(active_sheet)
# reading a cell
print(worksheet["A1"].value)
excel_data = list()
# iterating over the rows and
# getting value from each cell in row
for row in worksheet.iter_rows():
row_data = list()
for cell in row:
row_data.append(str(cell.value))
print(cell.value)
excel_data.append(row_data)
Product_Details.objects.all().delete()
Recommend_Prediction.objects.all().delete()
for r in range(1, active_sheet.max_row+1):
Product_Details.objects.create(
idno= active_sheet.cell(r, 1).value,
ProductId= active_sheet.cell(r, 2).value,
UserId= active_sheet.cell(r, 3).value,

23
 ProfileName= active_sheet.cell(r, 4).value,
HelpfulnessNumerator= active_sheet.cell(r, 5).value,
HelpfulnessDenominator= active_sheet.cell(r, 6).value,
Score= active_sheet.cell(r, 7).value,
Time= active_sheet.cell(r, 8).value,
Summary= active_sheet.cell(r, 9).value,
Review= active_sheet.cell(r, 10).value )

return render(request, 'RUser/Add_DataSet_Details.html',

{"excel_data": excel_data})
def Register1(request):
if request.method == "POST":
username = request.POST.get('username')
email = request.POST.get('email')
password = request.POST.get('password')
phoneno = request.POST.get('phoneno')
country = request.POST.get('country')
state = request.POST.get('state')
city = request.POST.get('city')
ClientRegister_Model.objects.create(username=username,
email=email, password=password, phoneno=phoneno,
country=country,
state=state,
city=city)

return render(request, 'RUser/Register1.html')

else:
return render(request,'RUser/Register1.html')

def ViewYourProfile(request):
userid = request.session['userid']
obj = ClientRegister_Model.objects.get(id= userid)
return render(request,'RUser/ViewYourProfile.html',
{'object':obj})

def Search_DataSets(request):
if request.method == "POST":
kword = request.POST.get('keyword')
if request.method == "POST":
kword = request.POST.get('keyword')
df = pd.read_csv('Reviews.csv')
df
df.columns
df.rename(columns={'Score': 'Rating', 'Text':
'Review'}, inplace=True)

24
 def apply_recommend(Rating):
if (Rating <= 2):
return 0 # No Recommend
else:
return 1 # Recommend

df['recommend'] = df['Rating'].apply(apply_recommend)
df.drop(['Rating'], axis=1, inplace=True)
recommend = df['recommend'].value_counts()
df.drop(
['Id', 'ProductId', 'UserId', 'ProfileName',
'HelpfulnessNumerator', 'HelpfulnessDenominator', 'Time',
'Summary'], axis=1, inplace=True)

cv = CountVectorizer()
X = df['Review']
y = df['recommend']
X = cv.fit_transform(X)

models = []
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,
y, test_size=0.20)
X_train.shape, X_test.shape, y_train.shape

print("Naive Bayes")

from sklearn.naive_bayes import MultinomialNB

NB = MultinomialNB()
models.append(('naive_bayes', NB))
# SVM Model
print("SVM")
from sklearn import svm
lin_clf = svm.LinearSVC()
lin_clf.fit(X_train, y_train)
models.append(('svm', lin_clf))

print("Logistic Regression")

from sklearn.linear_model import LogisticRegression

reg = LogisticRegression(random_state=0,
solver='lbfgs').fit(X_train, y_train)
models.append(('logistic', reg))

classifier = VotingClassifier(models)
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)

25
 review_data = [kword]
vector1 = cv.transform(review_data).toarray()
predict_text = classifier.predict(vector1)

pred = str(predict_text).replace("[", "")

pred1 = pred.replace("]", "")

prediction = int(pred1)

if prediction == 0:
predict = 'No Recommend'
else:
predict = 'Recommend'

return render(request, 'RUser/Search_DataSets.html',

{'objs': predict})
return render(request, 'RUser/Search_DataSets.html')

26
6.2 Python:

Python is an interpreted, object-oriented, high-level programming language with

dynamic semantics. Its high-level built in data structures, combined with dynamic
typing and dynamic binding, make it very attractive for Rapid Application
Development, as well as for use as a scripting or glue language to connect existing
components together. Python's simple, easy to learn syntax emphasizes readability and
therefore reduces the cost of program maintenance. Python supports modules and
packages, which encourages program modularity and code reuse. The Python interpreter
and the extensive standard library are available in source or binary form without charge
for all major platforms, and can be freely distributed.

Often, programmers fall in love with Python because of the increased productivity
it provides. Since there is no compilation step, the edit-test-debug cycle is incredibly
fast. Debugging Python programs is easy: a bug or bad input will never cause a
segmentation fault. Instead, when the interpreter discovers an error, it raises an
exception. When the program doesn't catch the exception, the interpreter prints a stack
trace. A source level debugger allows inspection of local and global variables,
evaluation of arbitrary expressions, setting breakpoints, stepping through the code a line
at a time, and so on. The debugger is written in Python itself, testifying to Python's
introspective power. On the other hand, often the quickest way to debug a program is to
add a few print statements to the source: the fast edit-test-debug cycle makes this simple
approach very effective.

 Python is Interpreted: Python is processed at runtime by the interpreter. You

do not need to compile your program before executing it. This is similar to
PERL and PHP.

27
  Python is Interactive: You can actually sit at a Python prompt and interact
with the interpreter directly to write your programs.
 Python is Object-Oriented: Python supports Object-Oriented style or
technique of programming that encapsulates code within objects.
 Python is a Beginner's Language: Python is a great language for the beginner-
level programmers and supports the development of a wide range of
applications from simple text processing to WWW browsers to game.

6.3 Web Django Framework (Python):

Django is a high-level web framework for building robust and scalable web
applications using the Python programming language. It follows the Model-View-
Controller (MVC) architectural pattern, emphasizing the reusability, maintainability,
and rapid development of web applications.

At the core of Django is its Object-Relational Mapping (ORM) system, which

allows developers to interact with the database using Python code rather than SQL
queries. This abstraction simplifies database operations, making it easier to manage data
models. Django's built-in admin interface further streamlines database management,
providing a convenient way to handle CRUD (Create, Read, Update, Delete) operations
without extensive coding.

Django's templating engine enables the separation of logic and presentation in web
applications. This encourages the creation of clean and maintainable code by allowing
developers to define dynamic content within HTML templates. The framework's URL
routing system organizes the application's structure, mapping URLs to specific views
and facilitating a clear and scalable project layout.

One of Django's notable features is its emphasis on security. The framework

includes built-in protection against common web vulnerabilities, such as SQL injection,
cross-site scripting (XSS), and cross-site request forgery (CSRF). This focus on security
simplifies the development process, as developers can rely on Django's defaults while
still having the flexibility to implement custom security measures.

Django follows the "Don't Repeat Yourself" (DRY) principle, providing reusable
components and a modular design. This promotes code efficiency and reduces

28
redundancy, allowing developers to focus on implementing unique features rather than
repetitive tasks. Additionally, Django's extensive ecosystem of third-party packages,
known as "Django apps," further accelerates development by offering pre-built solutions
for various functionalities.

29
 CHAPTER-7

TESTING

The following are the Testing Methodologies:

o Unit Testing
o Integration Testing
o User Acceptance Testing
o Output Testing
o Validation testing

7.1 Unit Testing:

Unit testing focuses verification effort on the smallest unit of Software design
that is the module. Unit testing exercises specific paths in a module’s control structure
to ensure complete coverage and maximum error detection. This test focuses on each
module individually, ensuring that it functions properly as a unit. Hence, the naming is
Unit Testing.
During this testing, each module is tested individually and the module interfaces
are verified for the consistency with design specification. All important processing path
are tested for the expected results. All error handling paths are also tested.
7.2 Integration Testing:

Integration testing addresses the issues associated with the dual problems of
verification and program construction. After the software has been integrated a set of
high order tests are conducted. The main objective in this testing process is to take unit
tested modules and builds a program structure that has been dictated by design.

The following are the types of Integration Testing:

7.2.1 Top-Down Integration:

This method is an incremental approach to the construction of program

structure. Modules are integrated by moving downward through the control hierarchy,
beginning with the main program module. The module subordinates to the main

30
program module are incorporated into the structure in either a depth first or breadth first
manner.
In this method, the software is tested from main module and
individual stubs are replaced when the test proceeds downwards.
7.2.2 Bottom-up Integration:
This method begins the construction and testing with the modules at the lowest
level in the program structure. Since the modules are integrated from the bottom up,
processing required for modules subordinate to a given level is always available and the
need for stubs is eliminated. The bottom up integration strategy may be implemented
with the following steps:

 The low-level modules are combined into clusters into clusters that
perform a specific Software sub-function.
 A driver (i.e.) the control program for testing is written to coordinate test
case input and output.
 The cluster is tested.
 Drivers are removed and clusters are combined moving upward in the
program structure
The bottom-up approaches tests each module individually and then each module
is module is integrated with a main module and tested for functionality.

7.3 User Acceptance Testing:

User Acceptance of a system is the key factor for the success of any system. The
system under consideration is tested for user acceptance by constantly keeping in touch
with the prospective system users at the time of developing and making changes
wherever required. The system developed provides a friendly user interface that can
easily be understood even by a person who is new to the system.

7.4 Output Testing:

After performing the validation testing, the next step is output testing of the
proposed system, since no system could be useful if it does not produce the required
output in the specified format. Asking the users about the format required by them tests

31
the outputs generated or displayed by the system under consideration. Hence the output
format is considered in 2 ways – one is on screen and another in printed format.

7.5 Validation Checking:

Validation checks are performed on the following fields.

7.5.1 Text Field:

The text field can contain only the number of characters lesser than or equal to
its size. The text fields are alphanumeric in some tables and alphabetic in other tables.
Incorrect entry always flashes and error message.
7.5.2 Numeric Field:

The numeric field can contain only numbers from 0 to 9. An entry of any
character flashes an error message. The individual modules are checked for accuracy
and what it has to perform. Each module is subjected to test run along with sample
data. The individually tested modules are integrated into a single system. Testing
involves executing the real data information is used in the program the existence of any
program defect is inferred from the output. The testing should be planned so that all
the requirements are individually tested.
A successful test is one that gives out the defects for the inappropriate data and
produces and output revealing the errors in the system.
7.5.3 Preparation of Test Data:

Taking various kinds of test data does the above testing. Preparation of test data
plays a vital role in the system testing. After preparing the test data the system under
study is tested using that test data. While testing the system by using test data errors are
again uncovered and corrected by using above testing steps and corrections are also
noted for future use.

7.5.4 Using Live Test Data:

Live test data are those that are actually extracted from organization files. After a
system is partially constructed, programmers or analysts often ask users to key in a set
of data from their normal activities. Then, the systems person uses this data as a way to

32
partially test the system. In other instances, programmers or analysts extract a set of live
data from the files and have them entered themselves.

It is difficult to obtain live data in sufficient amounts to conduct extensive

testing. And, although it is realistic data that will show how the system will perform for
the typical processing requirement, assuming that the live data entered are in fact
typical, such data generally will not test all combinations or formats that can enter the
system. This bias toward typical values then does not provide a true systems test and in
fact ignores the cases most likely to cause system failure.

7.5.5 Using Artificial Test Data:

Artificial test data are created solely for test purposes, since they can be
generated to test all combinations of formats and values. In other words, the artificial
data, which can quickly be prepared by a data generating utility program in the
information systems department, make possible the testing of all login and control paths
through the program.

The most effective test programs use artificial test data generated by persons
other than those who wrote the programs. Often, an independent team of testers
formulates a testing plan, using the systems specifications.

The package “Virtual Private Network” has satisfied all the requirements
specified as per software requirement specification and was accepted.

USER TRAINING:

Whenever a new system is developed, user training is required to educate them

about the working of the system so that it can be put to efficient use by those for whom
the system has been primarily designed. For this purpose the normal working of the
project was demonstrated to the prospective users. Its working is easily understandable
and since the expected users are people who have good knowledge of computers, the
use of this system is very easy.

MAINTAINENCE:

This covers a wide range of activities including correcting code and design
errors. To reduce the need for maintenance in the long run, we have more accurately

33
defined the user’s requirements during the process of system development. Depending
on the requirements, this system has been developed to satisfy the needs to the largest
possible extent. With development in technology, it may be possible to add many more
features

based on the requirements in future. The coding and designing is simple and easy to
understand which will make maintenance easier.

TESTING STRATEGY:
A strategy for system testing integrates system test cases and design techniques
into a well planned series of steps that results in the successful construction of software.
The testing strategy must co-operate test planning, test case design, test execution, and
the resultant data collection and evaluation. A strategy for software testing must
accommodate low-level tests that are necessary to verify that a small source code
segment has been correctly implemented as well as high level tests that validate major
system functions against user requirements.

Software testing is a critical element of software quality assurance and

represents the ultimate review of specification design and coding. Testing represents an
interesting anomaly for the software. Thus, a series of testing are performed for the
proposed system before the system is ready for user acceptance testing.

SYSTEM TESTING:

Software once validated must be combined with other system elements (e.g.
Hardware, people, database). System testing verifies that all the elements are proper and
that overall system function performance is achieved. It also tests to find discrepancies
between the system and its original objective, current specifications and system
documentation.

UNIT TESTING:

In unit testing different are modules are tested against the specifications
produced during the design for the modules. Unit testing is essential for verification of
the code produced during the coding phase, and hence the goals to test the internal logic
of the modules. Using the detailed design description as a guide, important Conrail
paths are tested to uncover errors within the boundary of the modules. This testing is

34
carried out during the programming stage itself. In this type of testing step, each module
was found to be working satisfactorily as regards to the expected output from the
module.

In Due Course, latest technology advancements will be taken into consideration.

As part of technical build-up many components of the networking system will be
generic in nature so that future projects can either use or interact with this. The future
holds a lot to offer to the development and refinement of this project.

35
 CHAPTER-8

OUTPUT SCREENS

8.1 User Registration Page:

Fig.8.1. User Registration page

8.2 Service Provider Login Page:

36
 Fig.8.2. Service Provider Login Page

8.3 User Login Page:

Fig.8.3. User Login Page

8.4 Post Product Data Sets:

37
 Fig.8.4. Post Product Data Sets

8.5 User Profile Details:

Fig.8.5 User Profile Details

8.6 Prediction of Product Recommendation:

38
 Fig.8.6. Prediction of Product Recommendation

8.7 Product Recommendation With Prediction:

Fig.8.7. Product Recommendation With Prediction

8.8 Trained and Tested Data Sets Results:

39
 Fig.8.8. Trained and Tested Data Sets Results

8.9 Details of Remote Users:

Fig.8.9. Details of Remote Users

8.10 View Trained and Accuracy in Bar Graph:

40
 Fig.8.10. View Trained and Accuracy Bar Graph

8.11 View Trained and Tested Accuracy Results:

Fig.8.11. View Trained and Tested Accuracy Results

8.12 Predict Product Recommendation From Data Set Details:

41
 Fig.8.12. Predict Product Recommendation From Data Set Details

CHAPTER-9

CONCLUSION

In this paper, we have proposed a personality-aware product recommendation

system based on interest mining and meta path discovery, the system predicts the user’s
needs and the associated items. Products recommendation is computed by analysing the
user’s topical interest, and eventually recommend the items associated with the those
interests. The proposed system is personality-aware from two aspects, firstly because it
incorporates the user’s personality traits to predict his topics of interest. Secondly, it
matches the user’s personality facets with the associated items. Experimental results
show that the proposed system outperforms the state-of-art schemes in terms of
precision and recall especially in the cold start phase for new items and users.

However, Meta-Interest could be improved in different aspects:

42
 1) In this work, the users’ personality traits measurement was conducted
through questionnaires. Integrating automatic personality recognition system, that can
detect the users’ personality traits based on their shared data, into Meta-Interest is one of
our future directions.
2) The proposed system uses Big-Five to model the user’ personality
Extending Meta-Interest to include other personality traits models such as the Myers–
Briggs type indicator is a future direction.
3) The proposed system could be further improved by integrating a
knowledge graph and infer topic-item association using semantic reasoning.

CHAPTER-10
FUTURE SCOPE

The future scope of a personality-aware product recommendation system, rooted

in user interest mining and metapath discovery, is poised for remarkable advancements.
As technology evolves, there are several avenues to explore, enhancing the system's
capabilities and user experience.
The future of personality-aware product recommendation systems lies in
dynamic personality profiling with deep learning, leveraging natural language
processing for nuanced interest mining, advancing metapath discovery through graph
theory, real-time data integration for up-to-date recommendations, and prioritizing
ethical considerations. User feedback loops will ensure continuous improvement,
fostering a more personalized and trustworthy experience.

43
 CHAPTER-11

REFERENCE

[1] G. Piao and J. G. Breslin, “Inferring user interests in microblogging social networks:
a survey,” User Modelling and User-Adapted Interaction, vol. 28, no. 3, pp. 277–329,
aug 2018. [Online]. Available: http://link.springer.com/10.1007/s11257-018-9207-8
[2] A. Vinciarelli and G. Mohammadi, “A Survey of Personality Computing,” IEEE
Transactions on Affective Computing, vol. 5, no. 3, pp. 273–291, jul 2014. [Online].
Available: http://ieeexplore.ieee.org/document/6834774/
[3] V. Marteınez, F. Berzal, and J.-C. Cubero, “A Survey of Link Prediction in Complex
Networks,” ACM Computing Surveys, vol. 49, no. 4, pp. 1–33, feb 2017.
[4] H.-C. Yang and Z.-R. Huang, “Mining personality traits from social messages for
game recommender systems,” Knowledge-Based Systems, vol. 165, pp. 157–168, feb

44
2019.[Online].Available:
https://linkinghub.elsevier.com/retrieve/pii/S095070511830577X
[5] W. Wu, L. Chen, and Y. Zhao, “Personalizing recommendation diversity based on
user personality,” User Modelling and User-Adapted Interaction, vol. 28, no. 3, pp. 237–
276, 2018.
[6] H. Ning, S. Dhelim, and N. Aung, “PersoNet: Friend Recommendation System
Based on Big-Five Personality Traits and Hybrid Filtering,” IEEE Transactions on
Computational Social Systems, pp. 1–9, 2019.
[Online]. Available: https://ieeexplore.ieee.org/document/8675299/
[7] B. Ferwerda, M. Tkalcic, and M. Schedl, “Personality Traits and Music Genres:
What Do People Prefer to Listen To?” in Proceedings of the 25th Conference on User
Modeling, Adaptation and Personalization.
ACM, 2017, pp. 285–288.
[8] B. Ferwerda, E. Yang, M. Schedl, and M. Tkalcic, “Personality and taxonomy
preferences, and the influence of category choice on the user experience for music
streaming services,” Multimedia Tools and Applications, pp. 1–34, 2019. [9] Z. Yusefi
Hafshejani, M. Kaedi, and A. Fatemi, “Improving sparsity and new user problems in
collaborative filtering by clustering the personality factors,” Electronic Commerce
Research, vol. 18, no. 4, pp. 813–836, dec 2018. [Online]. Available:
http://link.springer.com/10.1007/s10660- 018-9287-x
[10] S. Dhelim, N. Huansheng, S. Cui, M. Jianhua, R. Huang, and K. I.-K. Wang,
“Cyberentity and its consistency in the cyber-physical-social-thinking hyperspace,”
Computers & Electrical Engineering, vol. 81, p. 106506, jan 2020.[Online].Available:
https://linkinghub.elsevier.com/retrieve/pii/S0045790618334839
[11] A. Khelloufi, H. Ning, S. Dhelim, T. Qiu, J. Ma, R. Huang, and L. Atzori, “A Social
Relationships Based Service Recommendation System For
SIoT Devices,” IEEE Internet of Things Journal, pp. 1–1, 2020. [Online]. Available:
https://ieeexplore.ieee.org/document/9167284/
[12] F. Zarrinkalam, M. Kahani, and E. Bagheri, “Mining user interests over active
topics on social networks,” Information Processing & Management, vol. 54, no. 2, pp.
339–357, 2018.

45
[13] A. K. Trikha, F. Zarrinkalam, and E. Bagheri, “Topic-Association Mining for User
Interest Detection,” in European Conference on Information Retrieval. Springer, 2018,
pp. 665–671.
[14] J. Wang, W. X. Zhao, Y. He, and X. Li, “Infer user interests via link structure
regularization,” ACM Transactions on Intelligent Systems and Technology (TIST), vol.
5, no. 2, p. 23, 2014.
[15] S. Dhelim, H. Ning, M. A. Bouras, and J. Ma, “Cyber-Enabled Human-Centric
Smart Home Architecture,” in 2018 IEEE SmartWorld). IEEE, oct 2018, pp. 1880–
1886. [Online]. Available: https://ieeexplore.ieee.org/document/8560294/
[16] S. Faralli, G. Stilo, and P. Velardi, “Automatic acquisition of a taxonomy of
microblogs users’ interests,” Web Semantics: Science, Services and Agents on the World
Wide Web, vol. 45, pp. 23–40, 2017.
[17] S. Dhelim, N. Aung, and H. Ning, “Mining user interest based on personality-
aware hybrid filtering in social networks,” Knowledge-Based Systems, p. 106227, jul
2020. [Online]. Available:
https://linkinghub.elsevier.com/retrieve/pii/S0950705120304354
[18] J. Kang and H. Lee, “Modeling user interest in social media using news media and
wikipedia,” Information Systems, vol. 65, pp. 52–64, 2017.
[19] Qi Liu, Enhong Chen, Hui Xiong, C. H. Q. Ding, and Jian Chen, “Enhancing
Collaborative Filtering by User Interest Expansion via Personalized Ranking,” IEEE
Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 42, no. 1,
pp. 218–233, feb 2012. [Online]. Available:
http://ieeexplore.ieee.org/document/6006538/
[20] Y. Dong, N. V. Chawla, and A. Swami, “metapath2vec: Scalable Representation
Learning for Heterogeneous Networks,” in Proceedings of the 23rd ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining. New York, NY,
USA:ACM,aug2017,pp.135–144.[Online].Available:
https://dl.acm.org/doi/10.1145/3097983.3098036
[21] C. Shi, B. Hu, W. X. Zhao, and P. S. Yu, “Heterogeneous Information Network
Embedding for Recommendation,” IEEE Transactions on Knowledge and Data
Engineering,vol.31,no.2,pp.357–370,feb2019.[Online].Available:
https://ieeexplore.ieee.org/document/8355676/

46
[22] M. Zhang and Y. Chen, “Link prediction based on graph neural networks,” in
Advances in Neural Information Processing Systems, 2018, pp. 5165–5175.
[23] W. Song, Z. Xiao, Y. Wang, L. Charlin, M. Zhang, and J. Tang, “Session-Based
Social Recommendation via Dynamic Graph Attention Networks,” in Proceedings of
the Twelfth ACM International Conference on Web Search and Data Mining. New York,
NY, USA:ACM,jan2019,pp.555–563.[Online].Available:
https://dl.acm.org/doi/10.1145/3289600.3290989
[24] P. I. Armstrong and S. F. Anthoney, “Personality facets and RIASEC interests: An
integrated model,” Journal of Vocational Behavior, vol. 75, no. 3, pp. 346–359, dec
2009. [Online]. Available:
https://linkinghub.elsevier.com/retrieve/pii/S0001879109000657
[25] U. Wolfradt and J. E. Pretz, “Individual differences in creativity: Personality, story
writing, and hobbies,” European Journal of Personality,2001

47