TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 866–871, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics TakeLab at SemEval-2017 Task 5: Linear Aggregation of Word Embeddings for Fine-Grained Sentiment Analysis on Financial News Leon Rotim, Martin Tutek, Jan Šnajder Text Analysis and Knowledge Engineering Lab Faculty of Electrical Engineering and Computing, University of Zagreb Unska 3, 10000 Zagreb, Croatia {leon.rotim,martin.tutek,jan.snajder}@fer.hr Abstract This paper describes our system for fine- grained sentiment scoring of news head- lines submitted to SemEval 2017 task 5, subtask 2. Our system uses a feature-light method that consists of a Support Vector Regression (SVR) with various kernels and word embedding vectors as features. Our best-performing submission scored 3rd on the task out of 29 teams and 4th out of 45 submissions, with a cosine score of 0.733. 1 Introduction Sentiment analysis (Pang and Lee, 2008) is a task of predicting whether the text expresses a posi- tive, negative, or neutral opinion in general or with respect to an entity of interest. Developing sys- tems capable of performing highly accurate senti- ment analysis has attracted considerable attention over the last two decades. The topic has been one of the main research areas in recent shared tasks, with main focus on social media texts, which are of particular interest for social studies (O’Connor et al., 2010; Wang et al., 2012) and marketing anal- ysis (He et al., 2013; Yu et al., 2013). At the same time, social media texts pose a big challenge for sentiment analysis due to their short, informal and often ungrammatical format. This work focuses on the second subtask of SemEval-2017 Task 5, which aims to perform fine- grained sentiment analysis of the financial news. Given that sentiments can affect market dynam- ics (Goonatilake and Herath, 2007; Van de Kauter et al., 2015), sentiment analysis of financial news can be a powerful tool for predicting market reac- tions. Similar to social media posts, finance news are short texts, but, unlike social media posts, the text is edited and hence grammatically correct. On the other hand, news headlines are notorious for the use of a specific language (Reah, 2002), which is often elliptical and compressed, and thus differs from the language used in the rest of the news story. Many approaches to sentiment analysis resort to rich, domain-specific, hand-crafted features (Wil- son et al., 2009; Abbasi et al., 2008). At the same time, there has been a growing interest in feature- light methods, including kernel-methods (Culotta and Sorensen, 2004; Lodhi et al., 2002a; Srivastava et al., 2013) and neural embeddings (Maas et al., 2011; Socher et al., 2013). These methods alleviate the need for manual creation of domain-specific features, while maintaining high accuracy. Most of the recently published work focuses on sentiment analysis problems that are framed as a classifica- tion task, while fine-grained analysis is framed as a regression problem. However, most of the high per- forming classification methods can be easily tuned to perform regression. In this …

Content truncated to 500 words