Combining Cluster-Based Profiling Based on Social Media Features and Association Rule Mining for Personalised Recommendations of Touristic Activities

Abstract

Tourists who visit a city for the first time may find it difficult to decide on places to visit, as the amount of information in the Web about cultural and leisure activities may be large. Recommender systems address this problem by suggesting the points of interest that fit better with the user’s preferences. This paper presents a novel recommender system that leverages tweets to build user profiles, taking into account not only their personal preferences but also their travel habits. Association rules, which are mined from the previous visits of users documented on Twitter, are used to make the final recommendations of places to visit. The system has been applied to data of the city of Barcelona, and the results show that the use of the social media-based clustering procedure increases its performance according to several relevant metrics.

Multi Objective Genetic Algorithm for Optimal Route Selection from a Set of Recommended Touristic Activities

“…Our previous recommender system utilises trace data provided on Twitter to build user profiles that capture the interests and travel habits of tourists for recommending a set of related POIs considering their popularity and category. A full description of data collection, preprocessing and the recommendation process can be found at [5]. The output POIs from the recommender system are used in the MOGA to find the solution that fits better the requirements.…”

“…• Diversity: This objective ensures that the solution contains a diverse set of POIs. POIs are categorised in [5] using a hierarchical structure called an Activity Tree. As such, POIs are diverse when they share less categories and subcategories in their path.…”

“…As such, POIs are diverse when they share less categories and subcategories in their path. • Popularity: This objective ensures that the ratio of popular POIs in the solution matches the tourist's degree of interest in popular POIs (computed in [5] as the percentage of tweets sent from popular spots). • Preference: This objective ensures that the POIs in the solution are interesting to the tourist.…”

“…time, distance, budget), and then they evaluate possible solutions from a list of Points of Interest (POIs) based on these constraints while ensuring solutions match tourist preferences [2,3,4]. Our proposed method extends our previous work [5], which recommends a set of POIs that match the user's preference considering their relatedness. It addresses the problem of selecting and ordering a subset of the recommendable POIs to minimize the distance between them and maximize their diversity while maintaining the ratio of popular POIs and types of POIs preferred by the user.…”

Association Rules Mining for Hospital Readmission: A Case Study

“…The recommender system provides recommendation services to the aforementioned users based on personalised preferences to alleviate online information traffic [21]. Thus, Orama et al [22] presented potential ARM benefits in tourism recommenders following social media-based clustering for user profiles. In Chen and Deng [23], ARM in video-learning recommendations were utilised to observe students' interest following the individuals' learning behaviours in the network, while Hang et al [21] implemented the optimal travel route recommender system.…”