0% found this document useful (0 votes)
10 views8 pages

Twitter Analysis

H

Uploaded by

Hello Honeyy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
0% found this document useful (0 votes)
10 views8 pages

Twitter Analysis

H

Uploaded by

Hello Honeyy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 8
A Project Report On NLP and Sentimental analysis of Twitter Submitted to RAJIV GANDHI UNIVERSITY OF KNOWLEDGE AND TECHNOLOGIES, RK VALLEY, KADAPA in partial fulfillment of the requirements for the award of the Degree of BACHELOR OF TECHNOLOGY IN ELECTRONICS AND COMMUNICATION ENGINEERING Submitted by LHussaina 170417 G.Prasuna_—_R170097 J.SomaShekar R170398 Under the Guidance of B.Shaik Mohammad Rafi , Assistant Professor (®X) shor DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING RAJIV GANDHI UNIVERSITY OF KNOWLEDGE, TECHNOLOGIES (Catering the Educational Needs of Gifted Rural Youth of AP) R.K. Valley, Vempalli (M), Kadapa(dist)~ 516330 2019-2023 RAJIV GANDHI UNIVERSITY OF KNOWLEDGE TECHNOLOGIES (Catering the Educational Needs of Gifted Rural Youth of AP) R.K. Valley, Vempalli(M), Kadapa(dist)~ 516330 2019-2023 i aie ni i ATG es, RGUKT R.KValley CERTIFICATE, This is to certify that the project report entitled “ NLP and Sentimental analysis of twitter a bonafide record of the project work done and submitted by L.HUSSAINA _ (R170417) G.PRASUNA —_(R170097) J.SSOMASHEKAR (R170398) for the partial fulfillment of the requirements for the award of B.Tech. Degree in ELECTRONICS AND COMMUNICATION ENGINEERING,RGUKT, RK Valley, Kadapa. GUIDE ASSITANT PROFESSOR B.SHAIKMOHAMMAD RAFI P.JANARDHANA REDDY, INTERNAL EXAMINER EXTERNAL EXAMINER DECLARATION We here by declare that the project report entitled“ NLP & Sentimental Analysis of Twitter” submitted to the Department of ELECTRONICS AND. COMMUNICATION ENGINEERING in partial fulfillment of requirements for the award of the degree of BACHELOR OF TECHNOLOGY. This project is the result of Our own effort and that it has not been submitted to any other University ot Institution for the award of any degree or diploma other than specified above. L, Hussaina (R170417) G.Prasuna (R170097) J.Somashekar (R170938) ACKNOWLEDGEMENTS We are thankful to our guide Rafi sir and Head of the Department of ELECTRONICS AND COMMUNICATION ENGINEERING, Mr. B. MADHAN MOHAN for his valuabli ‘guidance and encouragement. His helping attitude and suggestions have helped us in the successful completion of the project. We have great pleasure in expressing our hearty thanks to our beloved Director Mrs. Sandhya Rani for spending her valuable time with us to complete this project. Successful completion of any project cannot be done without proper support and ‘encouragement. We sincerely thanks to the Management for providing all the necessary facilities during the course of study. ‘We would like to thank our parents and friends, who have the greatest contributions inall our achievements, for the great care and blessings in making us successful in all our endeavors. Yours Sincerely| L-Hussaina(R170417) G.Prasuna(R170097) NLP Course &Sentimental analysis of Twitter Abstract Social media is a popular network through which user can share their reviews about various topics, news, products etc.People use internet to access or update reviews so it is necessary to express opinion. Sentiment analysis is to| classify these reviews based on its opinion as either positive or negative category. First we have preprocessed the dataset to convert unstructured reviews into structured form. Then we have used lexicon based approach to convert structured review into numerical score value. In lexicon based approach we have preprocessed dataset using feature selection and semantic analysis. Stop word removal, stemming, POS tagging and calculating sentimen| score with help of SentiWordNet dictionary have been done in preprocessing part. Then we have applied classification algorithm to classifyopinion as either positive or negative. Support vector machine algorithm is used to classify reviews where RBF kernel SVM is modified by its hyper parameters which are| soft margin constant C , Gamma y. So optimized SVM gives good result than SVM and naive bayes. At last we have compared performance of all classifier with respect to accuracy. This Specialization is designed and taught by two experts in NLP, machine learning, and deep learning. Younes Bensouda Mourri is an Instructor of AI at Stanford University who also helped build the Deep Learning Specialization. Lukasz Kaiser is a Staff Research Scientist at Google Brain and the co-author of Tensorflow, the Tensor2Tensor and Trax libraries, and the Transformer paper. INTRODUCTON Sentiment analysis is an ongoing research area which is growing due to use of various applications, Sentiment analysis is also called as opinion mining. People give their reviews in form of unstructured format via blogs, forums ‘These unstructured reviews are preprocessed to extract opinion from it and this opinion is positive, negative or neutral. Sentiment analysis is done by using classification approaches which are lexicon and machine leaming based approaches, Lexicon based approach is of dictionary based approach and corpus based approach. Machine learning techniques are most widely used to classify and to predict sentiment as either positive or negative sentiment. Machine learning algorithms are mainly classified as either supervised or unsupervised approach. Supervised approach takes labeleddataset where each training set has already assigned its sentiment. Unsupervised approach takes unlabeled dataset where review is not defined with its label a) Perform sentiment analysis of tweets using logistic regression and then naive Bayes, b) Use vector space models to discover relationships between words and use PCA to reduce the dimensionality of the vector space and visualize those relationships, and ©) Write a simple English to French translation algorithm using pre-computed word embeddings and locality-sensitive hashing to relate words via approximate k-nearest neighbor search PROPOSED METHODOLOGY Step 1: Review Dataset Here we have used Polarity movie review dataset. Separate text file maintained for each review. Other Twitter and Gold dataset is also taken to show effect of proposed method on different dataset. Twitter dataset is taken from twitter APT and gold dataset is taken from amazon.com Step 2: Preprocessing Reviews contain information which are not expressive or say meaning and need to be removed. Step 3 : Classify by Optimized SVM ‘The preprocessed dataset is given as input to the classification algorithm. The Naive Bayes and Support Vector Machine classification algorithm is also used to classify dataset because of comparison with optimized SVM. Here we have changed value of kernel hyper parameters which are gamma and margin constant. Step 4 : Result Confusion Matrix is generated which shows classified positive and negative reviews. Accuracy is calculated based on confusion matrix. Then it has been compared with values of same with naive bayes and support vector machine, Naive Bayes Itis probabilistic classifier which requires small set of training data to determine parameter prediction. Only variance of feature is calculated because of independence of features instead of calculating full covariance matrix. Bayes theorem is defined as. P(cld)=P(d/cy P(A) dis review and c is class. For a given textual review ,d" and for a class ,c" (positive, negative), the conditional probability for each class given a review is P(c|d) CONCLUSION Sentiment analysis has been done for movie Review, Twitter and Gold dataset using optimized SVM. Here Comparison is made between Optimized Support Vector Machine towards Support Vector Machine and naive bayes classifier. Modifying hyper parameter value of RBF kemel SVM gives better result compare to Support Vector Machine and Naive Bayes algorithm. Hyper parameters are soft margin constant C and Gamma y. Proposed approach has found optimal value for hyper parameter which classifies dataset with more accuracy than existing system. ‘There are many SVM kemel functions available with many hyper parameters. These values can be modified to improve accuracy. REFERENCES (1) Liu, B., 2012, Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1), pp.1-167. [2}Pang, B., Lee, L. and Vaithyanathan, S., 2002, July. Thumbs up?: sentiment Classification using machine learning techniques. In Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10 (pp. 79-86). Association for Computational Linguistics. [3] Mouthami, K., Devi, K.N. and Bhaskaran, V.M., 2013, February. Sentiment analysis and classification based on textual reviews. In Information Communication and Embedded Systems (ICICES), 2013 Intemational Conference on (pp. 271-276). IEEE. [4] Go, A., Bhayani, R. and Huang, L., 2009, Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford, 1, p.12. [65 Kanakaraj, M. and Guddeti, R-MLR., 2015, February. Performance analysis of Ensemble methods on Twitter sentiment analysis using NLP techniques. In SemanticComputing (ICSC), 2015 IEEE International Conference on (pp. 169- 170). IEEE

You might also like