A Description of the Sentiment Analysis Task and Their Application for the Analysis of Tweets

Flora Pincock 2


In this paper we introduce the main fundamentals of sentiment analysis and the benefits of using the popular micro-blogging site, Twitter, as a source of texts for sentiment analysis. We review some of the most recent papers published on sentiment analysis and describe the most relevant methods and approaches. We have used the conclusions of current research in the field to decide which methods or techniques to use in our own experimentation of sentiment analysis. We identify the methods of evaluating the performance of classifiers, and the open source tools available for carrying out the analysis. For our research, we have used Twitter data from the Sentiment140 database. We have explored various combinations of feature selection methods and machine learning techniques to build and evaluate 20 classifiers using this data.


sentiment analysis; classification functions; feature selection; twitter.

Full Text:



Amazon. https://www.amazon.com/. Online, Accessed: May 2018.

Asur S, Huberman BA. 2010, Predicting the future with social media, IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), 492–499.

Cambria E, Schuller B, Xia Y, et al..New avenues in opinion mining and sentiment analysis, IEEE Intelligent Systems 2013; 28(2): 15–21.

English Oxford Dictionary. https://en.oxforddictionaries.com/. Online, Accessed: May 2018.

Graff M, Moctezuma D, Siordia OS, et al. A case study of Spanish text transformations for twitter sentiment analysis, Expert Systems with Applications, 2017; 81:457-471.

Gebremeskel G,Sentiment analysis of twitter posts about news, thesis, University of Malta 2011.

Hassan A, Abbasi A, Zeng D. Twitter sentiment analysis: a bootstrap ensemble framework, IEEE International Conference on Social Computing (SocialCom),2013; 357–364.

Hussein DMEDM, A survey on sentiment analysis challenges, Journal of King Saud University - Engineering Sciences, 2016; 1-9

Imdb. http://www.imdb.com/. Online, Accessed: May 2018.

Kang DHH, Yoo SJ. Senti-lexicon and improved naïve Bayes algorithms for sentiment analysis of restaurant reviews, Expert Systems with Applications,2012; 39:6000-6010.

Li TY, Li YM. Deriving market intelligence from microblogs, Decision Support Systems, 2013; 55(1):206-217..

Liu Y, Bi JW, Fan ZP. Multi-class sentiment classification: The experimental comparisons of feature selection and machine learning algorithms, Expert Systems with Applications, 2017; 80:323-339.

Medhat W, Hassan A, Korashy H.Sentiment analysis algorithms and applications: A survey, Ain Shams Engineering Journal, 2014; 5: 1093–1113.

Ravi K, Ravi V. A survey on opinion mining and sentiment analysis: Tasks, approaches and applications, Knowledge-Based Systems, 2015; 89: 14-46.

Sentiment140 database. http://help.sentiment140.com/for-students. Online, Accessed: May 2018.

Soleymani M, Garcia D, Jou B,et al. A survey of multimodal sentiment analysis, Image and Vision Computing, 2017; 65: 3-14.

Trip advisor. https://www.tripadvisor.com/. Online, Accessed: May 2018.

Tripathy A, Agrawal A, Rath SK.Classification of sentiment reviews using n-gram machine learning approach, Expert Systems with Applications, 2016; 57: 117-126.

Twitter. https://twitter.com/?lang=en. Online, Accessed: May 2018.

Twitter search API. https://dev.twitter.com/rest/public/search. Online, Accessed: May 2018.

Twitter statistics. https://www.brandwatch.com/blog/44-twitter-stats-2016/. Online, Accessed: May 2018.

Whinston A, Rui H, Liu Y.Whose and what chatter matters? the effect of tweets on movie sales, Decision Support Systems, 2013; 55(4):863-870.

Yousefpour A, Ibrahim R, Hamed HNA. Ordinal-based and frequency-based integration of feature selection methods for sentiment analysis, Expert Systems with Applications, 2017; 75: 80-93.

DOI: http://dx.doi.org/10.24294/csma.v0i0.860


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License

This site is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.