CISUC-KIS: Tackling Message Polarity Classification with a Large and Diverse Set of Features

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 166–170, Dublin, Ireland, August 23-24, 2014. CISUC-KIS: Tackling Message Polarity Classification with a Large and Diverse set of Features Jo˜ao Leal, Sara Pinto, Ana Bento, Hugo Gonc¸alo Oliveira, Paulo Gomes CISUC, Department of Informatics Engineering University of Coimbra Portugal {jleal,sarap,arbc}@student.dei.uc.pt, {hroliv,pgomes}@dei.uc.pt Abstract This paper presents the approach of the CISUC-KIS team to the SemEval 2014 task on Sentiment Analysis in Twitter, more precisely subtask B - Message Polar- ity Classification. We followed a machine learning approach where a SVM classifier was trained from a large and diverse set of features that included lexical, syntac- tic, sentiment and semantic-based aspects. This led to very interesting results which, in different datasets, put us always in the top-7 scores, including second position in the LiveJournal2014 dataset. 1 Introduction Everyday people transmit their opinion in social networks and microblogging services. Identifying the sentiment transmitted in all those shared mes- sages is of great utility for recognizing trends and supporting decision making, key in areas such as social marketing. Sentiment Analysis deals with the computational treatment of sentiments in nat- ural language text, often normalized to positive or negative polarities. It is a very challenging task, not only for machines, but also for humans. SemEval 2014 is a semantic evaluation of Nat- ural Language Processing (NLP) that comprises several tasks. This paper describes our approach to the Sentiment Analysis in Twitter task, which comprises two subtasks: (A) Contextual Polarity Disambiguation; and (B) Message Polarity Clas- sification. We ended up addressing only task B, which is more sentence oriented, as it targets the polarity of the full messages and not individual words in those messages. This work is licenced under a Creative Commons Attribution 4.0 International License. Page numbers and proceedings footer are added by the organizers. License details: http: //creativecommons.org/licenses/by/4.0/ We tackled this task with a machine learning- based approach, in which we first collect several features from the analysis of the given text at sev- eral levels. The collected features are then used to learn a sentiment classification model, which can be done with different algorithms. Features were collected from several different resources, includ- ing: sentiment lexicons, dictionaries and avail- able APIs for this task. Moreover, since micro- blogging text has particular characteristics that in- crease the difficulty of NLP, we gave special fo- cus on text pre-processing. Regarding the tested features, they went from low-level ones, such as punctuation and emoticons, to more high-level, including topics extracted using topic modelling techniques, as well features from sentiment lexi- cons, some structured on plain words and others based on WordNet, and thus structured on word senses. Using the latter, we even explored word sense disambiguation. We tested several learn- ing algorithms with all these features, but Support Vector Machines (SVM) led to the best results, so it was used for the final evaluation. In all our runs, a model was learned from tweets, and no SMS were used for training. The model’s performance …

Content truncated to 500 words