PotTS at SemEval-2016 Task 4: Sentiment Analysis of Twitter Using Character-level Convolutional Neural Networks.

Proceedings of SemEval-2016, pages 230–237, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics PotTS at SemEval-2016 Task 4: Sentiment Analysis of Twitter Using Character-level Convolutional Neural Networks. Uladzimir Sidarenka Applied Computational Linguistics/FSP Cognitive Science University of Potsdam Karl-Liebknecht Straße 24-25 14476 Potsdam sidarenk@uni-potsdam.de Abstract This paper presents an alternative approach to polarity and intensity classification of senti- ments in microblogs. In contrast to previous works, which either relied on carefully de- signed hand-crafted feature sets or automat- ically derived neural embeddings for words, our method harnesses character embeddings as its main input units. We obtain task-specific vector representations of characters by train- ing a deep multi-layer convolutional neural network on the labeled dataset provided to the participants of the SemEval-2016 Shared Task 4 (Sentiment Analysis in Twitter; Nakov et al., 2016b) and subsequently evaluate our classifiers on subtasks B (two-way polarity classification) and C (joint five-way prediction of polarity and intensity) of this competition. Our first system, which uses three manifold convolution sets followed by four non-linear layers, ranks 16 in the former track; while our second network, which consists of a sin- gle convolutional filter set followed by a high- way layer and three non-linearities with linear mappings in-between, attains the 10-th place on subtask C.1 1 Introduction Sentiment analysis (SA) – a field of knowledge which deals with the analysis of people’s opinions, sentiments, evaluations, appraisals, attitudes, and emotions towards particular entities mentioned in discourse (Liu, 2012) – is commonly considered to be one of the most challenging, competitive, but at 1The source code of our implementation is freely avail- able online at https://github.com/WladimirSidorenko/ SemEval-2016/ the same time utmost necessary areas of research in modern computational linguistics. Unfortunately, despite numerous notable ad- vances in recent years (e.g., Breck et al., 2007; Yessenalina and Cardie, 2011; Socher et al., 2011), many of the challenges in the opinion mining field, such as domain adaptation or analysis of noisy texts, still pose considerable difficulties to researchers. In this respect, rapidly evaluating and comparing dif- ferent approaches to solving these problems in a controlled environment – like the one provided for the SemEval task (Nakov et al., 2016b) – is of cru- cial importance for finding the best possible way of mastering them. We also pursue this goal in the present paper by investigating whether one of the newest machine learning trends – the use of deep neural networks (DNNs) with small receptive fields – would be a vi- able solution for improving state-of-the-art results in sentiment analysis of Twitter. After a brief summary of related work in Section 2, we present the architectures of our networks and describe the training procedure we used for them in Section 3. Since we applied two different DNN topologies to subtasks B and C, we make a cross- comparison of both systems and evaluate the role of the preprocessing steps in the next-to-last section. Finally, in Section 5, we draw conclusions from our experiments and make further suggestions for future research. 2 …

Content truncated to 500 words