Geo-semantic profiling of brand-specific customer experience using citizen-generated social media comments
Keywords: Geosemantic, geo-semantic, NLP, natural language processing
Abstract: A good customer experience is likely to influence a customer’s decision to buy positively and equally a negative customer experience will most likely make a customer decide not to buy or go elsewhere. One negative customer experience is likely enough to make a customer leave a brand, and go to a competitor. To conduct this research, labeled Twitter data was utilized, and the Spacy library was employed to extract location information from tweets. The sentiment analysis of the tweets, categorizing them into positive, negative, and neutral sentiments, was accomplished using the Vader lexicon. The Vader lexicon, a valuable resource available in the Natural Language Toolkit (NLTK), provided a basis for sentiment evaluation.
Submission Category: Machine learning algorithms
Submission Number: 51
Loading