User sentiment analysis-based travel recommendation method and system

Abstract

The invention discloses a user sentiment analysis-based travel recommendation method and system. The system comprises a preprocessing module and a recommendation module. The method comprises the steps of performing extraction to obtain travel place information shared by a target user and a corresponding sentiment factor during sharing of the travel place by the target user according to a user behavior of the target user in a social network; establishing a correlation between the corresponding sentiment factor during the sharing of the travel place by the target user and the travel place information shared by the target user to obtain correlated data of the target user; extracting the correlated data of the target user and performing similarity calculation; establishing a user list according to travel place information of similar users, and performing calculation to obtain interest values of the target user for all the travel place information shared by the users in the user list of the similar users; and obtaining a travel list and recommending the travel list to the target user. According to the method and the system, sentiment states of the user at different granularity levels and different time segments are extracted from the social network, thereby assisting the user to better explore and discover user preferences in travel scheme selection.

Description

technical field [0001] The invention belongs to the field of data processing, in particular to a travel recommendation method and system based on user emotion analysis. Background technique [0002] People have different preferences in the choice of travel and leisure destinations in different scenarios and states. At present, many recommendation systems have begun to consider combining various user-related background information, such as time, location, scene, weather and other mixed situations in the recommendation system to improve the accuracy of the recommendation. [0003] However, when a user is planning a travel plan, the influence of emotions on the user will often affect the final result. However, the user's emotional state is a typical secondary background information, because it cannot be directly measured, but needs to be inferred from other types of background information. Therefore, it is a very challenging task to obtain the user's emotional state in time a...

AI Technical Summary

Problems solved by technology

Although there are only a few recommendation systems on the market that try to extract and utilize users' emotions and make effective recommendations, there is still a blank space in the existing market for those recommendation products that focus on how emotions affect users' recommendations for travel and leisure travel.

Images