Abstract:
As digital marketing is becoming more popular, the number of customer views on brands is increasing rapidly. This makes it harder for companies to assess their brand imag...Show MoreMetadata
Abstract:
As digital marketing is becoming more popular, the number of customer views on brands is increasing rapidly. This makes it harder for companies to assess their brand image or digitally market their products on the web. We present a lexicon-based approach to extracting sentiment and emotion from tweets for digital marketing purposes. We collect ten thousand tweets related to ten technology brands: Apple, Google, Microsoft, Samsung, GE, IBM, Intel, Facebook, Oracle and HP. We perform sentiment analysis using SentiWordNet while we detect emotions using the NRC Hashtag Emotion Lexicon. We compare and combine the scores obtained from the two lexicons into one result per tweet. We describe the execution process of our experiment and show that the accuracy of the combined approach of sentiment and emotion analysis is enhanced over the independent approaches of sentiment analysis or emotion analysis.
Published in: 2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)
Date of Conference: 03-05 November 2015
Date Added to IEEE Xplore: 21 December 2015
ISBN Information: