Sentiment Intensity Ranking among Adjectives Using Sentiment Bearing Word Embeddings

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 547–552 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Sentiment Intensity Ranking among Adjectives Using Sentiment Bearing Word Embeddings Raksha Sharma, Arpan Somani, Lakshya Kumar, Pushpak Bhattacharyya Dept. of Computer Science and Engineering IIT Bombay, India raksha,somani,lakshya,pb@cse.iitb.ac.in Abstract Identification of intensity ordering among polar (positive or negative) words which have the same semantics can lead to a fine- grained sentiment analysis. For exam- ple, master, seasoned and familiar point to different intensity levels, though they all convey the same meaning (semantics), i.e., expertise: having a good knowledge of. In this paper, we propose a semi- supervised technique that uses sentiment bearing word embeddings to produce a continuous ranking among adjectives that share common semantics. Our system demonstrates a strong Spearman’s rank correlation of 0.83 with the gold standard ranking. We show that sentiment bear- ing word embeddings facilitate a more ac- curate intensity ranking system than other standard word embeddings (word2vec and GloVe). Word2vec is the state-of-the-art for intensity ordering task. 1 Introduction The interchangeable use of semantically simi- lar words stimulates sentiment intensity variation among sentences. To understand the phenomenon, let us consider the following example: 1. (a) We were pleased by the beauty of the island. (Positively low intense) (b) We were delighted by the beauty of the island. (Positively medium intense) (c) We were exhilarated by the beauty of the island. (Positively high intense) Pleased, Exhilarated and delighted are the posi- tive words bearing the same semantics, i.e., direct- ing the emotion, but their use intensifies the posi- tive sentiment in the sentences 1(a), 1(b) and 1(c) respectively. Identification of intensity ranking among the words which have the same semantics can facilitate such a fine-grained sentiment analy- sis as exemplified in 1(a), 1(b) and 1(c).1 In this paper, we present a semi-supervised ap- proach to establish a continuous intensity ranking among polar adjectives having the same seman- tics. Essentially, our approach is a refinement of the work done by Sharma et al., (2015). They also built a system that generates intensity of the words that bear the same semantics; however, their system considers only three discrete intensity lev- els, viz., low, medium and high. The important feature of our approach is that it uses Sentiment Specific Word Embeddings (SSWE). SSWE are an enhancement to the normal word embeddings with respect to the sentiment analysis task (Tang et al., 2014). SSWE capture syntactic, semantic as well as sentiment information, unlike normal word embeddings (word2vec and GloVe), which capture only syntactic and semantic information. Our Contribution: We propose an approach that generates a continuous (finer) intensity rank- ing among polar words, which belong to the same semantic category. In addition, we show that SSWE produce a significantly better inten- sity ranking scale than word2vec (Mikolov et al., 2013) and GloVe (Pennington et al., 2014), which do not capture sentiment information of the words. The remaining paper is organized as follows. Section 2 describes the …

Content truncated to 500 words