Scribd
Upload
43 views

Sentiment Analysis Using DL

The document summarizes sentiment analysis and deep learning techniques. It discusses how sentiment analysis uses natural language processing and machine learning to identify subjective information like feelings in texts. Deep learning approaches for sentiment analysis include convolutional neural networks (CNNs) and recurrent neural networks (RNNs) like LSTMs. The document also outlines challenges in sentiment analysis like reducing time complexity, handling complex syntax, and improving accuracy.

Uploaded by

pranavkanthavel7709
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
43 views

Sentiment Analysis Using DL

The document summarizes sentiment analysis and deep learning techniques. It discusses how sentiment analysis uses natural language processing and machine learning to identify subjective information like feelings in texts. Deep learning approaches for sentiment analysis include convolutional neural networks (CNNs) and recurrent neural networks (RNNs) like LSTMs. The document also outlines challenges in sentiment analysis like reducing time complexity, handling complex syntax, and improving accuracy.

Uploaded by

pranavkanthavel7709
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 20

3rd International Conference on

3rd International Conference on Sentiment Analysis and


Deep Learning (ICSADL 2024),
13-14, March 2024 ✤ Bhimdatta, Nepal.
(ICSADL 2024)
13-14, March 2024 ✤ Bhimdatta, Nepal

Sentiment Analysis and


Deep Learning
Prof. Dr. R. KANTHAVEL
Professor of Computer Engineering, ECE Dept.,
Papua New Guinea University of Technology,
Sentiment Analysis & Deep Learning 3/13/2024 Papua New Guinea.
1
SENTIMANT ANALYSIS
 Sentiment analysis is a form of text research that
uses a mix of statistics, natural language processing
(NLP), and machine learning to identify and extract
subjective information — for instance, a reviewer's
feelings, thoughts, judgments, or assessments
about a particular topic, event, or a company and
its activities.

Sentiment Analysis & Deep Learning 3/13/2024 2


Why sentiment analysis?
 Movie: Is this review positive or negative?
 Products: What do people think about the new
iPhone?
 Public sentiment: How is consumer confidence? Is
despair increasing?
 Politics: What do people think about this candidate or
issue?
 Prediction: Predict election outcomes or market
trends from sentiment
Sentiment Analysis & Deep Learning 3/13/2024 3
Affective States
 Emotion: brief organically synchronized evaluation of a major event •
angry, sad, joyful, fearful, ashamed, proud, elated
 Mood: diffuse non-caused low-intensity long-duration change in
subjective feeling • cheerful, gloomy, irritable, listless, depressed,
buoyant
 Interpersonal stances: affective stance toward another person in a
specific interaction • friendly, flirtatious, distant, cold, warm, supportive,
contemptuous
 Attitudes: enduring, affectively colored beliefs, dispositions towards
objects or persons • liking, loving, hating, valuing, desiring
 Personality traits: stable personality dispositions and typical behavior
tendencies • nervous, anxious, reckless, morose, hostile, jealous
Sentiment Analysis & Deep Learning 3/13/2024 4
Sentiment Analysis
 Sentiment analysis is the detection of attitudes “enduring,
affectively colored beliefs, dispositions towards objects or persons”
 1. Holder (source) of attitude
 2. Target (aspect) of attitude
 3. Type of attitude
From a set of types • Like, love, hate, value, desire, etc.
• Or (more commonly) simple weighted polarity: • positive,
negative, neutral, together with strength
4. Text containing the attitude
• Sentence or entire document
Sentiment Analysis & Deep Learning 3/13/2024 5
Sentiment Analysis
 Simplest task:
 •Is the attitude of this text positive or negative?

 More complex:
 •Rank the attitude of this text from 1 to 5

 Advanced:
 •Detect the target, source, or complex attitude
Sentiment Analysis & Deep Learning 3/13/2024
types6
Sentiment Analysis using Deep Learning

Data Collection
Processing
Analysis
Visualization

Sentiment Analysis & Deep Learning 3/13/2024 7


Extracting Features for Sentiment
Classification
How to handle negation?
• I didn’t like this movie
Versus
• I really like this movie
Which words to use?
• Only adjectives
• All words
All words turns out to work better, at least on this data.

Sentiment Analysis & Deep Learning 3/13/2024 8


Deep Learning
 One or more hidden layers and the ability to have
trainable parameters in these layers.
 An artificial network, that is organized in
hierarchical layers, has the capability to build
hierarchical representations of the input data.

Sentiment Analysis & Deep Learning 3/13/2024 9


Sentiment analysis
 Sentiment analysis is a collection of methods with the
main intent to observe the opinion or
attitude,

For example, of a sentence expressed in


natural language.
Sentiment Analysis & Deep Learning 3/13/2024 10
Positive or negative movie review?

 Unbelievably disappointing
 Full of zany characters and richly applied
satire, and some great plot twists
 This is the greatest screwball comedy ever
filmed
 It was pathetic. The worst part about it was
the boxing scenes.
Sentiment Analysis & Deep Learning 3/13/2024 11
Google Product Review

Sentiment Analysis & Deep Learning 3/13/2024 12


Bing Shopping

Sentiment Analysis & Deep Learning 3/13/2024 13


Two main approaches
Two main approaches:

Convolutional neural networks (CNN)


Recurrent neural networks (RNN), can
be enhanced by using LSTM
Sentiment Analysis & Deep Learning 3/13/2024 14
Sentiment analysis using CNNs

 A simple CNN with one layer of convolution on top of word


vectors obtained from an unsupervised neural language
model.
 Good results are obtained by using pre-trained word vector.
 Results are still improved by further training the word
vectors for specific tasks.

Sentiment Analysis & Deep Learning 3/13/2024 15


Sentiment analysis using RNNs
 The word vectors created by co-occurrence statistics are not
always suitable for sentiment analysis (e.g. words “good” and
“bad” are close in word2vec representations).

 Sentiments are expressed by phrases instead of individual


words -> how to capture the representation of the whole
sentence?

 Additional challenge: Recurrent Neural Network (RNN) has


difficulties to maintain longer time dependencies -> LSTM
networks.
Sentiment Analysis & Deep Learning 3/13/2024 16
Statistical machine learning models

 Naive Bayes Classifier,


 Support Vector Machine (SVM),
 Logistic Regression, Random Forest,
 and Gradient Boosting Machines (GBM)

Sentiment Analysis & Deep Learning 3/13/2024 17


DEEP LEARNING APPROACHES

Sentiment Analysis & Deep Learning 3/13/2024 18


CHALLENGES
1.To reduce higher time complexity in sentiment
analysis.

2.To handle the syntactic dependency for


complex sentence.

3.To increase accuracy in sentiment classification.


Sentiment Analysis & Deep Learning 3/13/2024 19
Sentiment Analysis & Deep Learning 3/13/2024 20

You might also like