Tweester at SemEval-2016 Task 4: Sentiment Analysis in Twitter Using Semantic-Affective Model Adaptation

Proceedings of SemEval-2016, pages 155–163, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics Tweester at SemEval-2016 Task 4: Sentiment Analysis in Twitter using Semantic-Affective Model Adaptation Elisavet Palogiannidi2,3,1, Athanasia Kolovou4,1, Fenia Christopoulou1, Filippos Kokkinos1, Elias Iosif1,3,Nikolaos Malandrakis5, Harris Papageorgiou3, Shrikanth Narayanan5,6, Alexandros Potamianos1,3,6 1 School of ECE, National Technical University of Athens, Zografou 15780, Athens, Greece 2 School of ECE, Technical University of Crete, Chania 73100, Crete, Greece 3 “Athena” Research and Innovation Center, Maroussi 15125, Athens, Greece 4 Department of Informatics, University of Athens, Athens, Greece 5 Signal Analysis and Interpretation Laboratory (SAIL), USC, Los Angeles, CA 90089, USA 6 Behavioral Informatix, Los Angeles, CA 90089, USA epalogiannidi@isc.tuc.gr, akolovou@di.uoa.gr, el10136@mail.ntua.gr el11142@mail.ntua.gr, iosife@central.ntua.gr, malandra@usc.edu xaris@ilsp.athena-innovation.gr, shri@sipi.usc.edu, potam@central.ntua.gr Abstract We describe our submission to SemEval2016 Task 4: Sentiment Analysis in Twitter. The proposed system ranked first for the sub- task B. Our system comprises of multiple in- dependent models such as neural networks, semantic-affective models and topic modeling that are combined in a probabilistic way. The novelty of the system is the employment of a topic modeling approach in order to adapt the semantic-affective space for each tweet. In addition, significant enhancements were made in the main system dealing with the data pre- processing and feature extraction including the employment of word embeddings. Each model is used to predict a tweet’s sentiment (positive, negative or neutral) and a late fusion scheme is adopted for the final decision. 1 Introduction Nowadays, the usage of social networks such as Twitter dominates the daily communication of hun- dreds of millions of people around the world. People often share opinions and express their feelings about various topics through social networks. Tasks such as opinion mining and sentiment analysis (Pang and Lee, 2008) have become very popular, since they can capture a large portion of the public opinion. The sentiment analysis of tweets was applied in various domains, such as commerce (Jansen et al., 2009), disaster management (Verma et al., 2011) or health (Chew and Eysenbach, 2010). This task is especially challenging due to the terse and in- formal writing style, the semantic diversity of con- tent, as well as the often “unconventional” gram- mar and orthography. Many computational sys- tems like those submitted to SemEval 2015 Task 10 (Rosenthal et al., 2015) incorporate bag-of-words models with Twitter-specific features like hashtags and emoticons (Davidov et al., 2010; B¨uchner and Stein, 2015). Word embeddings obtained from large amounts of tweets are used under the scope of an unsupervised approach for sentiment analysis (Astudillo et al., 2015). Additionally, deep learn- ing models have recently become very popular for Twitter sentiment analysis (Severyn and Moschitti, 2015). Topic modeling approaches for sentiment analysis can also be found in literature, e.g., (Mei et al., 2007; Lin and He, 2009; Lu et al., 2011; Alam et al., 2016; Rao, 2016) In this paper, we present systems submitted to the SemEval 2016 Task 4 (Nakov et al., 2016) that deal with the sentiment analysis of tweets on the sentence level. …

Content truncated to 500 words