A Sentiment Analysis Approach of Data Volatility for Consumer Satisfaction in the Fashion Industry
Source of Publication
2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019
© 2019 IEEE. Consumer satisfaction forms a critical part of every business and directly impacts on the ability to retain customers. The ability to measure and define indexes for consumer satisfaction can be very useful for businesses as these can be used to swiftly respond to customer needs accordingly. The consumer satisfaction data for certain products exhibit extreme volatility because of their short requirement duration. Hence, it is necessary to identify present consumer satisfaction in a timely manner. This research adopts the fast fashion industry as a case study due to the high volatile nature of its social media data, among several other characteristics that influenced the decision. The research focused on investigating existing sentiment analysis techniques and the development of a novel one for the fast fashion industry based on its peculiar characteristics. This involved the development of a novel sentiment analysis framework with a sentiment scaling technique, making use of data mining strategies towards obtaining, identifying and analysing fast fashion social media data, for the identification of consumer satisfaction.
Institute of Electrical and Electronics Engineers Inc.
semantic role labelling, sentiment analysis, social data mining
Al-Obeidat, Feras; Hani, Anoud Bani; Benkhelifa, Elhadj; Adedugbe, Oluwasegun; and Majdalawieh, Munir, "A Sentiment Analysis Approach of Data Volatility for Consumer Satisfaction in the Fashion Industry" (2019). All Works. 266.
Indexed in Scopus