Mining public opinion: a sentiment based forecasting for democratic elections of Pakistan

다국어 초록 (Multilingual Abstract)

Twitter has emerged as outstanding and most prominent social media in today’s technological age. The data proliferates in quick and words with its activities trigger get fast responses from the users. This platform is perfect for promoting political perspectives, particularly when election campaigns are on its peak. Political trends on Twitter media has been contemplated in the course of recent years. In the past research, both supervised and unsupervised methodologies have been used to analyze the Twitter trends. Most of the Tweet classification approaches utilized built in Dictionaries, Naı¨ve Bayes, K-Nearest Neighbors (KNN), decision tree and Support Vector Machines (SVM) classifiers. However, in case of democratic election these trends can be mined to predict the winning party. However, all such approaches produce poor results due to language issues, low accuracy, limited access to internet and lower literacy rate in less developed countries such as Pakistan. This research study, find the best possible way for collection of tweets related to different political parties and build a prediction model that may analyze sentiments and opinions expressed by peoples in their Tweets. In this research work, a prediction based model along with novel similarity measure has been proposed to predict the election results of political parties in Pakistan. The proposed work is composed of data collection, preprocessing, aspect extraction, aspect refinement and final prediction using Bayesian theorem. Form the experimental results, it is concluded that proposed approach perform better than existing techniques by obtaining almost 98% accuracy and efficiently cover the limitations of existing studies.

참고문헌 (Reference)

1 Parackal, M, "Value-based prediction of election results using natural language processing : A case of the New Zealand General Election" 60 (60): 156-168, 2018

2 Ceron, A, "Using sentiment analysis to monitor electoral campaigns : Method matters evidence from the United States and Italy" 33 (33): 3-20, 2015

3 Asemah, E. S, "Use of social media in the 2015 presidential election in Nigeria" 11 (11): 4-11, 2017

4 Jungherr, A, "Twitter use in election campaigns : A systematic literature review" 13 (13): 72-91, 2016

5 Salunkhe, P, "Twitter based election prediction and analysis" 4 (4): 539-544, 2017

6 Enli, G, "Twitter as arena for the authentic outsider:Exploring the social media campaigns of Trump and Clinton in the 2016 US presidential election" 32 (32): 50-61, 2017

7 Liu, D, "The appeal to political sentiment: An analysis of Donald Trump’s and Hillary Clinton’s speech themes and discourse strategies in the 2016 US presidential election" 25 : 143-152, 2018

8 Lewis-Beck, M. S, "The Political Economy model : 2016 US election forecasts" 49 (49): 661-663, 2016

9 Jacobs, K, "Social Media, Parties, and Political Inequalities" Springer 45-73, 2016

10 Yaqub, U, "Sentiment based analysis of tweets during the us presidential elections" 1-10, 2017

11 Singh, A. K, "Sentiment analysis of Twitter user data on Punjab legislative assembly election, 2017" 9 (9): 60-, 2017

12 Whitford, L, "RhymeZone Retrieved"

13 Singh, P, "Progress in Advanced Computing and Intelligent Engineering" Springer 665-673, 2018

14 Nooralahzadeh, F, "Presidential Elections on Twitter–An Analysis of How the US and French Election were Reflected in Tweets" 240-246, 2012

15 Wang, L, "Prediction of the 2017 French election based on Twitter data analysis" 89-93, 2017

16 Sharma, P, "Prediction of indian election using sentiment analysis on hindi twitter" 1966-1971, 2016

17 Razzaq, M. A, "Prediction and analysis of Pakistan election 2013 based on sentiment analysis" 700-703, 2013

18 Kim, S, "Populism and anti-populism in the 2017 Dutch, French, and German elections: A discourse and hegemony analytic approach" MISC 2018

19 Karami, A, "Mining public opinion about economic issues: Twitter and the us presidential election" 9 (9): 18-28, 2018

20 Mahmood, T, "Mining Twitter big data to predict 2013 Pakistan election winner" 49-54, 2013

21 Gayo-Avello, D, "Limits of electoral predictions using twitter" 2011

22 Soon, C, "General Election 2015 in Singapore : What social media did and did not do" 105 (105): 171-184, 2016

23 Singh, P, "Forecasting the 2016 US Presidential Elections Using Sentiment Analysis" 412-423, 2017

24 Ceron, A, "Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens political preferences with an application to Italy and France" 16 (16): 340-358, 2014

25 Wills-Otero, L, "Elections and Parties in Latin America:Ruptures and Continuities at the End of a Decade" SciELO Brasil 2019

26 Ramteke, J, "Election result prediction using Twitter sentiment analysis" 1 : 1-5, 2016

27 Kassraie, P, "Election Vote Share Prediction using a Sentiment-based Fusion of Twitter Data with Google Trends and Online Polls" 363-370, 2017

28 Hodson, J, "Diversity in Canadian election-related Twitter discourses : Influential voices and the media logic of# elxn42 and# cdnpoli hashtags" 16 (16): 307-323, 2019

29 Li, T, "Differentially private Naive Bayes learning over multiple data sources" 444 : 89-104, 2018

30 Hoang, T, "Crowdsensing and analyzing micro-event tweets for public transportation insights" IEEE 2157-2166, 2016

31 Murthy, D, "Comparing print coverage and tweets in elections: A case study of the 2011–2012 US Republican primaries" 33 (33): 298-314, 2015

32 Driscoll, K, "Big bird, binders, and bayonets:Humor and live-tweeting during the 2012 US presidential debates" 3 : 2012

33 Almatrafi, O, "Application of location-based sentiment analysis using Twitter for identifying trends towards Indian general elections 2014" 2015

34 Agarwal, A, "Application of Lexicon based approach in sentiment analysis for short tweets" 189-193, 2018

35 Nawaz, A, "A segregational approach for determining aspect sentiments in social media analysis" 75 (75): 2584-2602, 2019

36 Salunkhe, P, "A review:Prediction of election using Twitter sentiment analysis" 6 (6): 723-, 2017

37 Wicaksono, A. J, "A proposed method for predicting US presidential election by analyzing sentiment in social media" 276-280, 2016

38 Bermingham, A, ". On using Twitter to monitor political sentiment and predict election results" 2-10, 2011