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.

旅游业正在进入一个以消费者力量通过社交媒体的活力为特征的知识变革阶段。大量的互联网知识已成为全球通过电子邮件和社交网络进行交流的第一大手段。任何互联网用户都可以就任何主题（包括公司）自由表达自己的观点和感受。目前的研究旨在通过结合主题建模和基于词典的算法来提供一种新技术，以深入了解马拉喀什的电子声誉，提升该城市的旅游体验。本研究探讨了来自摩洛哥马拉喀什不同地点和景点的大约 39,216 条 TripAdvisor 评论。这种方法主要基于潜在狄利克雷分配（LDA），