Think Positive: Towards Twitter Sentiment Analysis from Scratch

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 647–651, Dublin, Ireland, August 23-24, 2014. Think Positive: Towards Twitter Sentiment Analysis from Scratch C´ıcero Nogueira dos Santos Brazilian Research Lab IBM Research cicerons@br.ibm.com Abstract In this paper we describe a Deep Convo- lutional Neural Network (DNN) approach to perform two sentiment detection tasks: message polarity classification and con- textual polarity disambiguation. We apply the proposed approach for the SemEval- 2014 Task 9: Sentiment Analysis in Twit- ter. Despite not using any handcrafted feature or sentiment lexicons, our system achieves very competitive results for Twit- ter data. 1 Introduction In this work we apply a recently proposed deep convolutional neural network (dos Santos and Gatti, 2014) that exploits from character- to sentence-level information to perform sentiment analysis of Twitter messages (tweets). The net- work proposed by dos Santos and Gatti (2014), named Character to Sentence Convolutional Neu- ral Network (CharSCNN), uses two convolutional layers to extract relevant features from words and messages of any size. We evaluate CharSCNN in the unconstrained track of the SemEval-2014 Task 9: Sentiment Analysis in Twitter (Rosenthal et al., 2014). Two subtasks are proposed in the SemEval-2014 Task 9: the contextual polarity disambiguation (Sub- taskA), which consists in determining the polar- ity (positive, negative, or neutral) of a marked word or phrase in a given message; and the message polarity classification (SubtaskB), which consists in classifying the polarity of the whole message. We use the same neural network to per- form both tasks. The only difference is that in This work is licenced under a Creative Commons Attribution 4.0 International License. Page numbers and proceedings footer are added by the organizers. License details: http: //creativecommons.org/licenses/by/4.0/ SubtaskA, CharSCNN is fed with a text segment composed by the words in a context window cen- tered at the target word/phrase. While in Sub- taskB, CharSCNN is fed with the whole message. The use of deep neural networks for sentiment analysis has been the focus of recent research. However, instead of convolutional neural network, most investigation has been done in the use of recursive neural networks (Socher et al., 2011; Socher et al., 2012; Socher et al., 2013). 2 Neural Network Architecture Given a segment of text (e.g. a tweet), CharSCNN computes a score for each sentiment label τ ∈ T = {positive, negative, neutral}. In order to score a text segment, the network takes as input the sequence of words in the segment, and passes it through a sequence of layers where features with increasing levels of complexity are extracted. The network extracts features from the character-level up to the sentence-level. 2.1 Initial Representation Levels The first layer of the network transforms words into real-valued feature vectors (embeddings) that capture morphological, syntactic and semantic in- formation about the words. We use a fixed- sized word vocabulary V wrd, and we consider that words are composed of characters from a fixed- sized character vocabulary V chr. Given a sen- tence consisting of N words {w1, w2, ..., …

Content truncated to 500 words