Real Time Classification of Political Tendency of Twitter Spanish Users based on Sentiment Analysis
What people say on social media has turned into a
rich source of information to understand social behavior. Specifically,
the growing use of Twitter social media for political communication
has arisen high opportunities to know the opinion of large numbers
of politically active individuals in real time and predict the global
political tendencies of a specific country. It has led to an increasing
body of research on this topic. The majority of these studies have
been focused on polarized political contexts characterized by only
two alternatives. Unlike them, this paper tackles the challenge
of forecasting Spanish political trends, characterized by multiple
political parties, by means of analyzing the Twitters Users political
tendency. According to this, a new strategy, named Tweets Analysis
Strategy (TAS), is proposed. This is based on analyzing the users
tweets by means of discovering its sentiment (positive, negative or
neutral) and classifying them according to the political party they
support. From this individual political tendency, the global political
prediction for each political party is calculated. In order to do this,
two different strategies for analyzing the sentiment analysis are
proposed: one is based on Positive and Negative words Matching
(PNM) and the second one is based on a Neural Networks Strategy
(NNS). The complete TAS strategy has been performed in a Big-Data
environment. The experimental results presented in this paper reveal
that NNS strategy performs much better than PNM strategy to analyze
the tweet sentiment. In addition, this research analyzes the viability
of the TAS strategy to obtain the global trend in a political context
make up by multiple parties with an error lower than 23%.
[1] M. Cmara, G. Cumbreras, V. Romn, and G. Morera, ”TASS 2015 The
Evolution of the Spanish Opinion Mining Systems” Procesamiento del
Lenguaje Natural, vol.56, 2016.
[2] J. Schmidhuber. 2015. Deep learning in neural
networks. Neural Netw. 61, C (January 2015), 85-117.
DOI=http://dx.doi.org/10.1016/j.neunet.2014.09.003
[3] B. Wellman, A. Quan Haase, J. Witte and K. Hampton. ”Does the Internet
Increase, Decrease, or Supplement Social Capital?: Social Networks,
Participation, and Community Commitment”, American Behavioral
Scientist, vol.45, n3, 2014, pp.436–455.
[4] Statista. ”Number of monthly Active Twitter Users Worldwide
from 1st quarter 2010 to 3rd quarter 2017 (in millions)”,
https://www.statista.com/statistics/282087/number-of-monthly-activetwitter-
users/, Date accessed: 01/12/2017.
[5] K. Lee, D. Palsetia, R. Narayanan, Md. Mostofa Ali Patwary, A.
Agrawal and A. Choudhary. ”Twitter Trending Topic Classification”. In
Proceedings of the IEEE 11th International Conference on Data Mining
Workshops (ICDMW ’11). IEEE Computer Society, 2011 pp.251–258.
[6] Beevolve. ”An Exhaustive Study of Twitter Users Across the
World”, http://temp.beevolve.com/twitter-statistics/, 2012, Date accessed:
01/12/2017.
[7] M.M. Uddin, M. Imran and H. Sajjad. ”Understanding Types of Users
on Twitter”, ArXiv e-prints, abs/1406.1335, 2014.
[8] L. De Silva and E. Riloff. ”User Type Classification of tweets with
Implications for Event Recognition”. Proceedings of the Joint Workshop
on Social Dynamics and Personal Attributes in Social Media, 2014,
pp.98–108.
[9] N. Mangal, R. Niyogi and A. Milani. ”Analysis of Users’ Interest Based
on tweets”, 16th International Conference on Computational Science and
Its Applications (ICCSA), 2016.
[10] M. Pennacchiotti and A. Popescu. ”A Machine Learning Approach to
Twitter User Classification”, A Machine Learning Approach to Twitter
User Classification, 2011, pp.281–288.
[11] EJ. Lee, SY. Shin. ”Are They Talking to Me? Cognitive and
Affective Effects of Interactivity in Politicians’ Twitter Communication”,
Cyberpsychology, behavior and social networking, vol.15, n.10, 2012,
pp.515–520.
[12] DS. Hillygus. The Evolution of Election Polling in the United States,
The Public Opinion Quarterly, vol.75, n.5, 2011, pp. 962-981.
[13] La Vanguardia. ”Bad Results in the Forecast of the Elections”,
http://www.lavanguardia.com/politica/elecciones/20160627/4027943145
38/sondeos-elecciones-generales-26j-fallo.html , June 27, 2016, Date
accessed: 01/12/2017 (Spanish version).
[14] W. Wanga, D. Rothschil, S. Goel, A. Gelman. ”Forecasting Elections
with Non-representative Polls”, International Journal of Forecasting,
Vol.31, Issue 3, 2015, pp. 980-991.
[15] D. Preotiuc-Pietro, Y. Liu, D. Hopkins, L. Ungar. ”Beyond Binary
Labels: political Ideology Prediction of Twitter Users”, Proceedings
of the 55th Annual Meeting of the Association for Computational
Linguistics, 2017, pp.729–740.
[16] A. Tumasjan, T. Sprenger, P. Sandner, and I. Welpe. ”Predicting
Elections with Twitter: What 140 Characters Reveal about political
Sentiment”, International AAAI Conference on Weblog and Social Media,
2010, pp.178–185.
[17] Preotiuc-Pietro, D.; Volkova, S.; Lampos, V.; Bachrach, Y. and Aletras,
N. Studying User Income through Language, Behaviour and Affect in
Social Media. PLoS ONE,10(9), 2015.
[18] K. Sylwester and M. Purver. ”Twitter Language Use Reflects
Psychological Differences between Democrats and Republicans”, PLoS
ONE, vol.10, n.9, 2015.
[19] MD. Conover, B. Gonalves, J. Ratkiewicz, A. Flammini and F.
Menczer. ”Predicting the political Alignment of Twitter Users”, IEEE
Third International Conference on Social Computing (SocialCom), 2011,
pp:192–199.
[20] Twitter Developers. ”Twitter API”, https://dev.twitter.com/, Date
accessed: 01/12/2017. [21] L. Jiang, M. Yu, M. Zhou, X. Liu and T. Zhao. ”Target-dependent Twitter
sentiment classification”, In Proceedings of the 49th Annual Meeting
of the Association for Computational Linguistics: Human Language
Technologies, 2011, pp.151–160.
[22] Y. Wang, Y. Rao, X. Zhan, H. Chen, M. Luo and J. Yin. ”Sentiment
and Emotion Classification over Noisy Labels”, Know.-Based Syst., 2016,
pp.207–216.
[23] W. Medhat, A.Hassan and H. Korashy. ”Sentiment Analysis Algorithms
and Applications: A survey”, In Ain Shams Engineering Journal, Vol.5,
Issue 4, 2014, pp.1093–1113.
[24] A. Agarwal, B. Xie, I. Vovsha, O. Rambow and R. Passonneau.
”Sentiment Analysis of Twitter Data”, In Proceedings of the Workshop
on Languages in Social Media (LSM ’11), 2011, pp.30–38.
[25] D. Grattarola. ”Twitter Sentiment Classification”,
https://github.com/danielegrattarola/twitter-sentiment-cnn, Date accessed:
1/12/2017.
[26] Hunspell. Hunspell is the spell checker, http://hunspell.github.io/, 2017,
Date accessed: 14/12/2017.
[27] TensorFlow. TensorFlow is an open source software library for numerical
computation using data flow graphs, https://www.tensorflow.org/, 2017,
Date accessed: 14/12/2017.
[28] Apache Storm. Apache Storm is a free and open source distributed
realtime computation system, http://storm.apache.org/, 2017, Date
accessed: 14/12/2017.
[29] OpenNebula. OpenNebula is a cloud computing platform for
managing heterogeneous distributed data center infrastructures,
https://opennebula.org/, 2017, Date accessed: 14/12/2017.
[1] M. Cmara, G. Cumbreras, V. Romn, and G. Morera, ”TASS 2015 The
Evolution of the Spanish Opinion Mining Systems” Procesamiento del
Lenguaje Natural, vol.56, 2016.
[2] J. Schmidhuber. 2015. Deep learning in neural
networks. Neural Netw. 61, C (January 2015), 85-117.
DOI=http://dx.doi.org/10.1016/j.neunet.2014.09.003
[3] B. Wellman, A. Quan Haase, J. Witte and K. Hampton. ”Does the Internet
Increase, Decrease, or Supplement Social Capital?: Social Networks,
Participation, and Community Commitment”, American Behavioral
Scientist, vol.45, n3, 2014, pp.436–455.
[4] Statista. ”Number of monthly Active Twitter Users Worldwide
from 1st quarter 2010 to 3rd quarter 2017 (in millions)”,
https://www.statista.com/statistics/282087/number-of-monthly-activetwitter-
users/, Date accessed: 01/12/2017.
[5] K. Lee, D. Palsetia, R. Narayanan, Md. Mostofa Ali Patwary, A.
Agrawal and A. Choudhary. ”Twitter Trending Topic Classification”. In
Proceedings of the IEEE 11th International Conference on Data Mining
Workshops (ICDMW ’11). IEEE Computer Society, 2011 pp.251–258.
[6] Beevolve. ”An Exhaustive Study of Twitter Users Across the
World”, http://temp.beevolve.com/twitter-statistics/, 2012, Date accessed:
01/12/2017.
[7] M.M. Uddin, M. Imran and H. Sajjad. ”Understanding Types of Users
on Twitter”, ArXiv e-prints, abs/1406.1335, 2014.
[8] L. De Silva and E. Riloff. ”User Type Classification of tweets with
Implications for Event Recognition”. Proceedings of the Joint Workshop
on Social Dynamics and Personal Attributes in Social Media, 2014,
pp.98–108.
[9] N. Mangal, R. Niyogi and A. Milani. ”Analysis of Users’ Interest Based
on tweets”, 16th International Conference on Computational Science and
Its Applications (ICCSA), 2016.
[10] M. Pennacchiotti and A. Popescu. ”A Machine Learning Approach to
Twitter User Classification”, A Machine Learning Approach to Twitter
User Classification, 2011, pp.281–288.
[11] EJ. Lee, SY. Shin. ”Are They Talking to Me? Cognitive and
Affective Effects of Interactivity in Politicians’ Twitter Communication”,
Cyberpsychology, behavior and social networking, vol.15, n.10, 2012,
pp.515–520.
[12] DS. Hillygus. The Evolution of Election Polling in the United States,
The Public Opinion Quarterly, vol.75, n.5, 2011, pp. 962-981.
[13] La Vanguardia. ”Bad Results in the Forecast of the Elections”,
http://www.lavanguardia.com/politica/elecciones/20160627/4027943145
38/sondeos-elecciones-generales-26j-fallo.html , June 27, 2016, Date
accessed: 01/12/2017 (Spanish version).
[14] W. Wanga, D. Rothschil, S. Goel, A. Gelman. ”Forecasting Elections
with Non-representative Polls”, International Journal of Forecasting,
Vol.31, Issue 3, 2015, pp. 980-991.
[15] D. Preotiuc-Pietro, Y. Liu, D. Hopkins, L. Ungar. ”Beyond Binary
Labels: political Ideology Prediction of Twitter Users”, Proceedings
of the 55th Annual Meeting of the Association for Computational
Linguistics, 2017, pp.729–740.
[16] A. Tumasjan, T. Sprenger, P. Sandner, and I. Welpe. ”Predicting
Elections with Twitter: What 140 Characters Reveal about political
Sentiment”, International AAAI Conference on Weblog and Social Media,
2010, pp.178–185.
[17] Preotiuc-Pietro, D.; Volkova, S.; Lampos, V.; Bachrach, Y. and Aletras,
N. Studying User Income through Language, Behaviour and Affect in
Social Media. PLoS ONE,10(9), 2015.
[18] K. Sylwester and M. Purver. ”Twitter Language Use Reflects
Psychological Differences between Democrats and Republicans”, PLoS
ONE, vol.10, n.9, 2015.
[19] MD. Conover, B. Gonalves, J. Ratkiewicz, A. Flammini and F.
Menczer. ”Predicting the political Alignment of Twitter Users”, IEEE
Third International Conference on Social Computing (SocialCom), 2011,
pp:192–199.
[20] Twitter Developers. ”Twitter API”, https://dev.twitter.com/, Date
accessed: 01/12/2017. [21] L. Jiang, M. Yu, M. Zhou, X. Liu and T. Zhao. ”Target-dependent Twitter
sentiment classification”, In Proceedings of the 49th Annual Meeting
of the Association for Computational Linguistics: Human Language
Technologies, 2011, pp.151–160.
[22] Y. Wang, Y. Rao, X. Zhan, H. Chen, M. Luo and J. Yin. ”Sentiment
and Emotion Classification over Noisy Labels”, Know.-Based Syst., 2016,
pp.207–216.
[23] W. Medhat, A.Hassan and H. Korashy. ”Sentiment Analysis Algorithms
and Applications: A survey”, In Ain Shams Engineering Journal, Vol.5,
Issue 4, 2014, pp.1093–1113.
[24] A. Agarwal, B. Xie, I. Vovsha, O. Rambow and R. Passonneau.
”Sentiment Analysis of Twitter Data”, In Proceedings of the Workshop
on Languages in Social Media (LSM ’11), 2011, pp.30–38.
[25] D. Grattarola. ”Twitter Sentiment Classification”,
https://github.com/danielegrattarola/twitter-sentiment-cnn, Date accessed:
1/12/2017.
[26] Hunspell. Hunspell is the spell checker, http://hunspell.github.io/, 2017,
Date accessed: 14/12/2017.
[27] TensorFlow. TensorFlow is an open source software library for numerical
computation using data flow graphs, https://www.tensorflow.org/, 2017,
Date accessed: 14/12/2017.
[28] Apache Storm. Apache Storm is a free and open source distributed
realtime computation system, http://storm.apache.org/, 2017, Date
accessed: 14/12/2017.
[29] OpenNebula. OpenNebula is a cloud computing platform for
managing heterogeneous distributed data center infrastructures,
https://opennebula.org/, 2017, Date accessed: 14/12/2017.
@article{"International Journal of Information, Control and Computer Sciences:77904", author = "Marc Solé and Francesc Giné and Magda Valls and Nina Bijedic", title = "Real Time Classification of Political Tendency of Twitter Spanish Users based on Sentiment Analysis", abstract = "What people say on social media has turned into a
rich source of information to understand social behavior. Specifically,
the growing use of Twitter social media for political communication
has arisen high opportunities to know the opinion of large numbers
of politically active individuals in real time and predict the global
political tendencies of a specific country. It has led to an increasing
body of research on this topic. The majority of these studies have
been focused on polarized political contexts characterized by only
two alternatives. Unlike them, this paper tackles the challenge
of forecasting Spanish political trends, characterized by multiple
political parties, by means of analyzing the Twitters Users political
tendency. According to this, a new strategy, named Tweets Analysis
Strategy (TAS), is proposed. This is based on analyzing the users
tweets by means of discovering its sentiment (positive, negative or
neutral) and classifying them according to the political party they
support. From this individual political tendency, the global political
prediction for each political party is calculated. In order to do this,
two different strategies for analyzing the sentiment analysis are
proposed: one is based on Positive and Negative words Matching
(PNM) and the second one is based on a Neural Networks Strategy
(NNS). The complete TAS strategy has been performed in a Big-Data
environment. The experimental results presented in this paper reveal
that NNS strategy performs much better than PNM strategy to analyze
the tweet sentiment. In addition, this research analyzes the viability
of the TAS strategy to obtain the global trend in a political context
make up by multiple parties with an error lower than 23%.", keywords = "Political tendency, prediction, sentiment analysis,
Twitter.", volume = "12", number = "9", pages = "697-10", }
