INF-UFRGS at SemEval-2017 Task 5: A Supervised Identification of Sentiment Score in Tweets and Headlines

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 837–841, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics INF-UFRGS at SemEval-2017 Task 5: A Supervised Identification of Sentiment Score in Tweets and Headlines Tiago Zini and Marcelo Dias and Karin Becker Instituto de Inform´atica (INF) Universidade Federal do Rio Grande do Sul Porto Alegre, RS, Brazil {tiago.zini, marcelo.dias, karin.becker}@inf.ufrgs.br Abstract This paper describes a supervised solu- tion for detecting the polarity scores of tweets or headline news in the financial domain, submitted to the SemEval 2017 Fine-Grained Sentiment Analysis on Fi- nancial Microblogs and News Task. The premise is that it is possible to understand market reaction over a company stock by measuring the positive/negative sentiment contained in the financial tweets and news headlines, where polarity is measured in a continuous scale ranging from -1.0 (very bearish) to 1.0 (very bullish). Our sys- tem receives as input the textual content of tweets or news headlines, together with their ids, stock cashtag or name of target company, and the polarity score gold stan- dard for the training dataset. Our solution retrieves features from these text instances using n-gram, hashtags, sentiment score calculated by a external APIs and others features to train a regression model capa- ble to detect continuous score of these sen- timents with precision. 1 Introduction Sentiment analysis involves the automatic identifi- cation of opinions, feelings, evaluations, attitudes expressed by people in the written language. A popular line of work in this field is opinion mining (Liu, 2012; Tsytsarau and Palpanas, 2012). Grow- ing attention has been dedicated to sentiment anal- ysis in the financial domain, given its links to mar- ket dynamics. The challenges are to detect how sentiment is expressed in documents in this do- main, and how it can translate to a reaction over a company stock, ranging from bullish to bear- ish. This problem is addressed as part of SemEval- 2017 (International Workshop on Semantic Evalu- ation 2017), Task 51. The task was defined as fol- lows: ”given a text instance (microblog message in Track 1, news statement or headline in Track 2), predict the sentiment score for each of the compa- nies/stocks mentioned. Sentiment values need to be floating point values in the range of -1 (very negative/bearish) to 1 (very positive/bullish), with 0 designating neutral sentiment.” The task was di- vided into two subtasks, according to the type of document (i.e. tweets and financial headlines) and sentiment target, and this paper describes our so- lution for both problems. We addressed these sub-tasks by building a su- pervised model to do regression of sentiment value in the documents based solely on their textual con- tent. The target of the sentiment in Task 5-1 is the company stocks for which two sets of annotated tweets were supplied: a training corpus with 1700 annotated tweets and a test corpus with 800 unan- notated tweets for task evaluation purpose. Two sets of news headlines were made available as part of Task …

Content truncated to 500 words