Use Supervise - unsupervised methods for tweet level Contextual semantics

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
© 2017 by IJETT Journal
Volume-47 Number-4
Year of Publication : 2017
Authors : Shilpi Goyal, Nirupama Tiwari


Shilpi Goyal, Nirupama Tiwari "Use Supervise - unsupervised methods for tweet level Contextual semantics", International Journal of Engineering Trends and Technology (IJETT), V47(4),222-225 May 2017. ISSN:2231-5381. published by seventh sense research group

Identifying the sentiments at tweet level based on contextual feature comes under text classification and clustering, an evolving area of wide research with many algorithms had been already proposed. With the recent advancements in the field of text mining there are many new techniques consistently emerging that need to be implemented for text classification in search of a better classifier. In this paper, we propose a lexicon based method that can remove the limitation of Senticircles. In this paper, we modify senticircle in the sense that senticircle tend to assign or update pre-assigned positive sentiments to negative or neutral one. The tweets are first parsed using open NLP, using this part of speech tagging to assign prior polarities. We in turn use partitioning around medoids method to take a sentiment of a term instead of senti-median method. We run evaluations on three datasets, @narendramodi , DeMonetization and #FightAgainstCorruption and shown through results whether our implementation of bag of words with its update sentiment with its strength gives a better performance for text based classification. Results show that the proposed method can achieve an accuracy of 71.34%, 72.98% and 71.37% with SVM, CTree and J48 classifier on datasets.


[1] Yassine, Mohamed, and Hazem Hajj. "A framework for emotion mining from text in online social networks." Data Mining Workshops (ICDMW), 2010 IEEE International Conference on. IEEE, 2010.
[2] Thelwall, Mike, et al. "Sentiment strength detection in short informal text." Journal of the American Society for Information Science and Technology 61.12 (2010): 2544-2558.
[3] Saif, Hassan, et al. "Contextual semantics for sentiment analysis of Twitter." Information Processing & Management 52.1 (2016): 5-19.
[4] Koto, Fajri, and Mirna Adriani. "The use of POS sequence for analyzing sentence pattern in Twitter sentiment analysis." Advanced Information Networking and Applications Workshops (WAINA), 2015 IEEE 29th International Conference on. IEEE, 2015.
[5] Pak, Alexander, and Patrick Paroubek. "Twitter as a Corpus for Sentiment Analysis and Opinion Mining." LREc. Vol. 10. No. 2010. 2010.
[6] Goyal, Shilpi, and Tiwari, Nirupama.”Emotion Recognition: A Literature Survey.” International Journal For Technological Research In Engineering Volume 4, Issue 9, May-2017

Sentiment Analysis, Text Mining, Contextual feature, Twitter, SentiCircles.