Application of fuzzy semantic similarity measures to event detection within tweets

Abstract

This paper examines the suitability of applying fuzzy semantic similarity measures (FSSM) to the task of detecting potential future events through the use of a group of prototypical event tweets. FSSM are ideal measures to be used to analyse the semantic textual content of tweets due to the ability to deal equally with not only nouns, verbs, adjectives and adverbs, but also perception based fuzzy words. The proposed methodology first creates a set of prototypical event related tweets and a control group of tweets from a data source, then calculates the semantic similarity against an event dataset compiled from tweets issued during the 2011 London riots. The dataset of tweets contained a proportion of tweets that the Guardian Newspaper publically released that were attributed to 200 influential Twitter users during the actual riot. The effects of changing the semantic similarity threshold are investigated in order to evaluate if Twitter tweets can be used in conjunction with fuzzy short text similarity measures and prototypical event related tweets to determine if an event is more likely to occur. By looking at the increase in frequency of tweets in the dataset, over a certain similarity threshold when matched with prototypical event tweets about riots, the results have shown that a potential future event can be detected.

Review of Survey Research in Fuzzy Approach for Text Mining

“…Abdul-Jaleel et al developed a new model to address the sentiment analysis problem, the method combines the feature set extracted from emotional sentences by genetic algorithm and fuzzy logic theory to improve the feature selection of emotional sentences, the results show that it is better than ordinary keyword feature selection [60]. AL-Deen et al proposed a sentiment classification method based on the fuzzy rule system, the research combined the fuzzy rule system that called FBPS, to extract features and used the crow algorithm (CSA) to strengthen the fuzzy output., the results found that compared with the existing machine learning methods, the results obtained higher accuracy [61], Dragoni & Pertucci proposed a method for multi-domain sentiment analysis by finding common word overlap through fuzzy methods [62], Crockett et al evaluated the Fuzzy Semantic Similarity Measure (FSSM) to analyze posts on social media to predict major events that may occur in the future, the results show that relevant keywords will ferment and spread on social media before potential events occur [63], Sassi et al believed that posts on social networks usually have several different emotions, so they proposed an automatic method based on semantic similarity measurement, using fuzzy classification to identify article emotions from online social software [64].…”

A Fuzzy Approach to Text Classification With Two-Stage Training for Ambiguous Instances

“…In addition, Dragoni et al proposed fuzzy approaches for exploiting opinion mining in computational advertising [40], undertaking concept-level sentiment analysis [41] and achieving multi-domain sentiment analysis [42]. Crockett et al evaluated the suitability of fuzzy semantic similarity measures for detection of potential future events and the results show that the detection can be achieved by using a group of prototypical event tweets [43]. An automatic approach based on a semantic similarity measure was introduced in [44] for recognizing emotion context from online social networks in the setting of fuzzy classification.…”