Creating emoji lexica from unsupervised sentiment analysis of their descriptions. (1st August 2018)

• Record Type: Journal Article
• Authors: Fernández-Gavilanes, Milagros; Juncal-Martínez, Jonathan; García-Méndez, Silvia; Costa-Montenegro, Enrique; González-Castaño, Francisco Javier
• Is Part Of: Expert systems with applications. Volume 103(2018)
• Page Start: 74
• Page End: 91
• Publication Date: 2018-08-01
• Subjects: Emoji analysis -- Sentiment analysis -- Opinion mining -- Nlp -- Artificial intelligence; 68Q55 -- 68T50; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.02.043
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Method to create emoji sentiment lexicon using unsupervised SA and Emojipedia. Unsupervised SA strategy based on semantic dependencies with propagation. Lexicon variants created considering sentiment distribution of messages with emojis. Lexica compare favorably well with other ones obtained manually or with CLDR names. Approach and variants applied to the Spanish, English and Spanish+English datasets. Abstract: Online media, such as blogs and social networking sites, generate massive volumes of unstructured data of great interest to analyze the opinions and sentiments of individuals and organizations. Novel approaches beyond Natural Language Processing are necessary to quantify these opinions with polarity metrics. So far, the sentiment expressed by emojis has received little attention. The use of symbols, however, has boomed in the past four years. About twenty billion are typed in Twitter nowadays, and new emojis keep appearing in each new Unicode version, making them increasingly relevant to sentiment analysis tasks. This has motivated us to propose a novel approach to predict the sentiments expressed by emojis in online textual messages, such as tweets, that does not require human effort to manually annotate data and saves valuable time for other analysis tasks. For this purpose, we automatically constructed a novel emoji sentiment lexicon using an unsupervised sentiment analysis system based on the definitions given by emoji creators inEmojipedia . Additionally, we automatically created lexicon variants by also considering the sentiment distribution of the informal texts accompanying emojis . All these lexica are evaluated and compared regarding the improvement obtained by including them in sentiment analysis of the annotated datasets provided by Kralj Novak, Smailovic, Sluban and Mozetic (2015). The results confirm the competitiveness of our approach.