HCS at SemEval-2017 Task 5: Polarity detection in business news using convolutional neural networks

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 842–846, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics HCS at SemEval-2017 Task 5: Sentiment Detection in Business News Using Convolutional Neural Networks Lidia Pivovarova Llorenc¸ Escoter Arto Klami Roman Yangarber Department of Computer Science University of Helsinki Finland first.last@cs.helsinki.fi Abstract Task 5 of SemEval-2017 involves fine- grained sentiment analysis on financial microblogs and news. Our solution for determining the sentiment score extends an earlier convolutional neural network for sentiment analysis in several ways. We explicitly encode a focus on a particular company, we apply a data augmentation scheme, and use a larger data collection to complement the small training data pro- vided by the task organizers. The best re- sults were achieved by training a model on an external dataset and then tuning it using the provided training dataset. 1 Introduction This paper describes our approach to Task 5 of the SemEval-2017 Challenge—fine-grained senti- ment analysis on financial microblogs and news. The task is to determine the sentiment score (posi- tive or negative) of a mention of a given company in a business-related text document—a microblog message (Track 1) or a news headline (Track 2). Our solution, “HCS,” is a convolutional neural network to classify sentiment scores. The model’s input takes two kinds of information: an article text, a list of focus points—positions in the text where a given company is mentioned. Foci allow the model to distinguish company mentions within the text, and to assign different scores to them. The data provided by the task organisers, (Handschuh et al., 2016), is short, one-sentence messages, with a given focus company. To train the model on additional data, we use the Named Entity (NE) recognition module of PULS (Yangar- ber and Steinberger, 2009; Huttunen et al., 2013; Atkinson et al., 2011), a news monitoring system, to find company mentions in arbitrary text. 2 Data The SemEval training set contains 1700 sentences for the microblog track and 1300 news headlines for the headline track, which is a very limited re- source for training flexible models. To compensate for the small size of the provided training sets, we built an extended training set. The PULS news monitoring system1 collects articles from a range of sources of business news (Pivovarova et al., 2013; Du et al., 2016). One of our data sources is a collection of news summaries written by business analysts, which contain metadata annotations. The metadata does not include sentiment scores. However, the metadata does provide labels that indicate business events mentioned in the article, e.g., Investment, Fraud or Merger. The labels are not mutually exclusive, and some documents may have more than one label. There are ap- proximately 300 labels, some of which imply— or weakly imply—positive or negative sentiment. However, most labels do not. We selected only those labels with the most clear sentiment implica- tions: e.g. Investment, New Product, Sponsorship, etc., are considered “positive,” while Fraud, Lay- off, Bankruptcy, etc., are considered “negative.” …

Content truncated to 500 words