XJSA at SemEval-2017 Task 4: A Deep System for Sentiment Classification in Twitter

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 728–731, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics ACL 2017 Submission ***. Confidential review Copy. DO NOT DISTRIBUTE. 1 000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 XJSA at SemEval-2017 Task 4：A Deep System for Sentiment Classification in Twitter Yazhou Hao Yangyang Lan University of Xi’an Jiaotong University of Xi’an Jiaotong yazhouhao@gmail.com 1564018606@qq.com Yufei Li Chen Li University of Xi’an Jiaotong University of Xi’an Jiaotong 18391819285@163.com cli@xjtu.edu.cn Abstract This paper describes the XJSA System submission from XJTU. Our system was created for SemEval2017 Task 4 – subtask A which is very popular and fundamental. The system is based on convolutional neural network and word embedding. We used two pre-trained word vectors and adopt a dynamic strategy for k-max pooling. 1 Introduction Several years ago, the typical approaches to sentiment analysis of tweets were based on classifiers trained using several hand-crafted features, in particular lexicons of words with an assigned polarity value. About since 2014 the deep neural network methods have got state-of- the-art results in many NLP tasks, especially in sentiment classification. The work of Harvard NLP group in 2014 and Kalchbrenner’s work in 2014 have suggested that convolutional neural network and word embedding play important roles in this field. General word embedding has got excellent results. If we can embed sentiment information in vectors, we will get better results. There are some open word vectors on the web already such as Word2Vec (Mikolov et al., 2013), Glove (Pennington et al., 2014), SSWE (Tang et al., 2014). In our system we use Word2Vec and SSWE at the same time. Deep learning models have achieved excellent results in computer vision and speech recognition in recent years. In the field of natural language processing, much work with deep learning methods has involved learning word vectors representations for their own task or problem (Bengio et al., 2003; Mikolov et al., 2013, Collobert C&W et al., 2011).The others exploit the open word vectors which was mentioned above.Word vectors is a transformation of the feature of letter,word,sentence and paragraph or even text. It’s a lower dimensional, dense and continuous vectors. In this vector, the words have similar syntactic are close – in Euclidean or cosine distance in the vector space. So one can study and compare the syntactic functionality between different words via word vectors. Convolutional neural network (CNN) utilize layers with convolutional filters that are applied …

Content truncated to 500 words