POLITICAL PREDICTION ANALYSIS USING TEXT MINING

“POLITICAL PREDICTION
ANALYSIS USING TEXT
MINING”
PAPER ID : 152
PRESENTED BY :
VISHWAMBHAR DESHPANDE
DINESH GAIKWAD
SNEHAL KOLHE
PRATIKSHA INDROL

INDEX
1. Introduction
2. Literature Overview
3. Proposed System
4. Objective
5. Scope
6. Methodology
7. Applications
8. Results
9. Conclusion
10. Future work
11. References

Introduction :
 Importance of election prediction using social media.
 Previous implementations & Their disadvantages.
 Technologies Used.

Sr. No Name Year Author Outcomes
[1] Opinion Mining And Sentiment Analysis, IEEE
International
Conference On Computing For Sustainable Global
Development,
2016 Rushlene Kaur Bakshi, Navneet
Kaur, Ravneet Kaur, Gurpreet Kaur
Configuration and system understanding
for sentiment analysis
[2] “Microblog Sentiment Analysis Algorithm Research
and Implementation Based on Classiﬁcation”
2015 Y. Yang and F. Zhou, Sentiment analysis and classification
algorithm
[3] A Parsimonious Rule based Model for Sentiment
Analysis of Social Media Text.
2014 Hutto, C.J. Gilbert, E.E. Social media impact using sentiment
analysis
[4] ”Sentiment analysis in twitter using machine learning
techniques.”
2013 Neethu, M. S., and R. Rajasree. Machine learning study using twitter as
platform
[5] “Sentiment analysis in twitter with lightweight
discourse analysis,”
2012 S. Mukherjee and P.
Bhattacharyya,
Discovery analysis in twitter
[6] “Towards enhanced opinion classiﬁcation using NLP
techniques,”
2011 A. Bakliwal, P. Arora, A. Patil, and
V. Varma,
Natural language processing and
classification algorithm
Literature Overview:

Sr. No Name Year Author Outcomes
[7] “Twitter sentiment classiﬁcation using distant
supervision,”
2009 A. Go, R. Bhayani, and L.
Huang
Distant supervision in sentiment analysis
[8] “A system for real-time twitter sentiment
analysis of 2012 us presidential election
cycle,”
2012 H. Wang, D. Can, A.
Kazemzadeh, F. Bar, and S.
Narayanan,
Live prediction on twitter data in election
campaign
[9] “ Sent iRank: CrossDomain Graph Ranking
for Sentiment Classiﬁcation,”
2009 Q. Wu, S. Tan, H. Zhai, G.
Zhang, M. Duan, and X.
Cheng,
Statistical representation using sentirank
[10] ”Cross-Domain Sentiment Analysis of Product
Reviews by Combining Lexicon-Based and
Learn-Based Techniques”
2015 K. Mao, J. Niu, X. Wang, L.
Wang and M. Qiu,
Lexicon based and learn based techniques
[11] ”Twitter as a corpus for sentiment analysis
and opinion mining”
2010 Alexander Pak and Patrick
Paroubek.
Opinion mining and sentiment analysis study
[12] “Twitter Based Election Prediction and
Analysis”
2017 Pritiee Salunkhe and Sachin
Deshmukh.
Prediction on twitter data
Literature Overview:

Proposed System (System Architecture)
Fig. Architecture of prediction using sentiment analysis

Proposed System :
 Importing Dataset from Twitter API
 Extracting dataset using Sqlite Server in the form of text & tabular data
 Data Preprocessing
 Classification algorithm implementation(Naïve Bayes Classification)
 Sentiment Analysis
 Statistical Representation

Objectives :
 To accept location based textual data from Twitter REST API and determine current
sentiment.
 To apply deep learning algorithm for historic data.
 To Predict using Sentiment Analysis based on live data in the form of graphs, trees,
reports, trends and Tweets.

Scope :
 Statistical data representation and deep learning improves accuracy better
than the other prediction models because of using live dataset rather than
processing on a stored dataset.

Methodology :
 Data Collection :
Data Collection Source.
Data Collection Method.
Twitter API Access Process.
 Twitter API Access :
Data Collection Request.
Data Storage.
Twitter API Access key.

Preprocessing :
 One of the most important goals of preprocessing is to enhance the quality of the data
by removing noise.
 The reduction of the feature space size.
1) Lower Case Conversion
2) Removing Punctuations and Removing Numbers
3) Stemming
4) Striping White Spaces

Sentiment Analysis :
 Machine Learning Approach :
 Supervised and unsupervised learning.
 Supervised learning used for prediction analysis.
 We used naive baye’s for classification.
Where,
P(A|B):Probability (conditional probability) of occurrence of event given the event B is
true.
P(A) and P(B): Probabilities of the occurrence of event A and B respectively.
P(B|A): Probability of the occurrence of event B given the event A is true.
P(A|B)=
P B A P(A)
P(B)

Applications :
 To know public opinions for political leaders and their Activities in terms of
Development.
 In business and Government intelligence for knowing customer attitudes and
trends in market.
 Detection of Insensitive data on social media platforms like Facebook, Twitter,
Instagram Etc.
 Resolving Customer Experiences for growing sales and prot.
 For Analyzing Social Media return of investment on social media marketing.

Conclusion :
Our system generates location based prediction in the form of statistical data.
The system uses Naive Bayes classifier, Natural Language Processing and Sentiment
analysis on Live data so it Improves Accuracy in Prediction Analysis.
Use of unsupervised learning algorithm reduces model training efforts as well.

Future Scope :
 In future multi lingual based sentiment analysis can be done to analyze tweets in
different languages for more Accurate Prediction.
 To increase the size of dataset by including big social media platforms like
Facebook, Linkedin for Sentiment Analysis.
 A strong Prediction Analysis system can be built to Analyze and Improve GDP &
growth in different sectors like Education, Defence, Culture and Manufacturing.

References :
 [1] Rushlene Kaur Bakshi, Navneet Kaur, Ravneet Kaur, Gurpreet Kaur, Opinion Mining And
Sentiment Analysis, IEEE International Conference On Computing For Sustainable Global
Development, October 2016.
 [2] Y. Yang and F. Zhou, “Microblog Sentiment Analysis Algorithm Research and Implementation
Based on Classiﬁcation”, 2015 14th International Symposium on Distributed Computing and
Applications for Business Engineering and Science (DCABES), 2015.
 [3] Hutto, C.J. Gilbert, E.E. (2014). VADER: A Parsimonious Rule based Model for Sentiment
Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media
(ICWSM-14). Ann Arbor, MI, June 2014.
 [4] Neethu, M. S., and R. Rajasree. ”Sentiment analysis in twitter using machine learning
techniques.” Computing, Communications and Networking Technologies (ICCCNT), 2013 Fourth
International Conference on. IEEE, 2013
 [5] S. Mukherjee and P. Bhattacharyya, “Sentiment analysis in twitter with lightweight discourse
analysis,” Proceedings of the 24th International Conference on Computational Linguistics
(COLING), pp. 1847–1864, Dec. 2012.
 [6] A. Bakliwal, P. Arora, A. Patil, and V. Varma, “Towards enhanced opinion classiﬁcation using
NLP techniques,” Proceedings of the Workshop on Sentiment Analysis where AI meets Psychology
(SAAIP), IJCNLP, pp, 101– 107, Nov. 2011.

References :
 [7] A. Go, R. Bhayani, and L. Huang, “Twitter sentiment classiﬁcation using distant supervision,”
CS224N Project Report, Stanford University, pp. 1–12, 2009.
 [8] H. Wang, D. Can, A. Kazemzadeh, F. Bar, and S. Narayanan, “A system for real-time twitter
sentiment analysis of 2012 us presidential election cycle,” Proceedings of the 50th Annual Meeting of
the Association for Computational Linguistics, pp 115–120, July 2012
 [9] Q. Wu, S. Tan, H. Zhai, G. Zhang, M. Duan, and X. Cheng,”Sent iRank: CrossDomain Graph
Ranking for Sentiment Classiﬁcation,” presented at the Proceedings of the 2009IEEE/WIC/ACM
International Joint Conference on Web Intelligence and Intelligent Agent Technology- Volume 01, 2009
 [10] K. Mao, J. Niu, X. Wang, L. Wang and M. Qiu, ”Cross-Domain Sentiment Analysis of Product
Reviews by Combining Lexicon-Based and Learn-Based Techniques”, 2015 IEEE 17th International
Conference on High Performance Computing and Communications, 2015 IEEE 7th International
Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on
Embedded Software and Systems, 2015.
 [11] Alexander Pak and Patrick Paroubek. ”Twitter as a corpus for sentiment analysis and opinion
mining”. In Proceedings of the Seventh International Conference on Language Resources and
Evaluation (LREC’10), may 2010.
 [12] Pritiee Salunkhe and Sachin Deshmukh. “Twitter Based Election Prediction and Analysis”,
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 10 October
2017

POLITICAL PREDICTION ANALYSIS USING TEXT MINING

POLITICAL PREDICTION ANALYSIS USING TEXT MINING

More Related Content

What's hot (10)

Similar to POLITICAL PREDICTION ANALYSIS USING TEXT MINING (20)

Recently uploaded (20)

POLITICAL PREDICTION ANALYSIS USING TEXT MINING