Exploring destination's negative e-reputation using aspect based sentiment analysis approach: Case of Marrakech destination on TripAdvisor

Tourism is entering a phase of intellectual changes characterized by consumer power's dynamism through social media. The immense amount of internet knowledge has become the number one means of communication globally through emails and social networks. Any Internet user can freely express themselves and give their views and feelings on any subject, including companies. The current research aims to provide a new technique by combining topic modeling and lexicon-based algorithms to gain insights about Marrakech's e-reputation, enhancing the tourism experience in this city. This study explores about 39,216 TripAdvisor reviews from different locations and attractions in Marrakech, Morocco. This approach is mainly based on Latent Dirichlet Allocation (LDA), to extract hidden aspects and dimensions from the feedbacks of tourists who visited Marrakech, search for some latent patterns inside the reviews and conduct Lexicon-based sentiment analysis to pinpoint the weaknesses directly and develop the touristic experience in this city.