DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 747–754, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis Christos Baziotis, Nikos Pelekis, Christos Doulkeridis University of Piraeus - Data Science Lab Piraeus, Greece mpsp14057@unipi.gr, npelekis@unipi.gr, cdoulk@unipi.gr Abstract In this paper we present two deep-learning systems that competed at SemEval-2017 Task 4 “Sentiment Analysis in Twitter”. We participated in all subtasks for En- glish tweets, involving message-level and topic-based sentiment polarity classifica- tion and quantification. We use Long Short-Term Memory (LSTM) networks augmented with two kinds of attention mechanisms, on top of word embeddings pre-trained on a big collection of Twitter messages. Also, we present a text process- ing tool suitable for social network mes- sages, which performs tokenization, word normalization, segmentation and spell cor- rection. Moreover, our approach uses no hand-crafted features or sentiment lexi- cons. We ranked 1st (tie) in Subtask A, and achieved very competitive results in the rest of the Subtasks. Both the word embeddings and our text processing tool1 are available to the research community. 1 Introduction Sentiment analysis is an area in Natural Language Processing (NLP), studying the identification and quantification of the sentiment expressed in text. Sentiment analysis in Twitter is a particularly chal- lenging task, because of the informal and “cre- ative” writing style, with improper use of gram- mar, figurative language, misspellings and slang. In previous runs of the Task, sentiment anal- ysis was usually tackled using hand-crafted fea- tures and/or sentiment lexicons (Mohammad et al., 2013; Kiritchenko et al., 2014; Palogiannidi et al., 2016), feeding them to classifiers such as Naive Bayes or Support Vector Machines (SVM). These approaches require a laborious 1github.com/cbaziotis/ekphrasis feature-engineering process, which may also need domain-specific knowledge, usually resulting both in redundant and missing features. Whereas, arti- ficial neural networks (Deriu et al., 2016; Rouvier and Favre, 2016) which perform feature learning, last year (Nakov et al., 2016) achieved very good results, outperforming the competition. In this paper, we present two deep-learning systems that competed at SemEval-2017 Task 4 (Rosenthal et al., 2017). Our first model is de- signed for addressing the problem of message- level sentiment analysis. We employ a 2-layer Bidirectional LSTM, equipped with an attention mechanism (Rocktäschel et al., 2015). For the topic-based sentiment analysis tasks, we propose a Siamese Bidirectional LSTM with a context- aware attention mechanism (Yang et al., 2016). In contrast to top-performing systems of previous years, we do not rely on hand-crafted features, sentiment lexicons and we do not use model en- sembles. We make the following contributions: • A text processing tool for text tokenization, word normalization, word segmentation and spell correction, geared towards Twitter. • A deep learning system for short-text senti- ment analysis using an attention mechanism, in order to enforce the contribution of words that determine the sentiment of a message. • A deep learning system for topic-based senti- ment analysis, with a context-aware attention …

Content truncated to 500 words