Tourism destination management using sentiment analysis and geo-location information: a deep learning approach

Abstract Sentiment analysis on social media such as Twitter is a challenging task given the data characteristics length, spelling errors, abbreviations, and special characters. Social sentiment also fundamental issue with many applications. With particular regard of tourism sector, where characterization fluxes vital issue, sources geotagged information have already proven to be promising for tourism-related geographic research. The paper introduces an approach estimate related Cilento’s, well known venue in Southern Italy. A newly collected dataset tweets at base our method. We aim demonstrating testing deep learning geodata framework characterize spatial, temporal demographic tourist flows across vast territory this rural touristic region along its coasts. applied four specially trained Deep Neural Networks identify assess sentiment, two word-level character-based, respectively. In contrast existing datasets, actual carried by texts or hashtags not automatically assessed approach. manually annotated whole set get higher quality terms accuracy, proving effectiveness Moreover, geographical coding labelling each information, allow fitting inferred sentiments their location, obtaining even more nuanced content semantic meaning.