Personalized Recommendation of PoIs to People with Autism

Abstract

The suggestion of Points of Interest to people with Autism Spectrum Disorder (ASD) challenges recommender systems research because these users' perception of places is influenced by idiosyncratic sensory aversions which can mine their experience by causing stress and anxiety. Therefore, managing individual preferences is not enough to provide these people with suitable recommendations. In order to address this issue, we propose a Top-N recommendation model that combines the user's idiosyncratic aversions with her/his preferences in a personalized way to suggest the most compatible and likable Points of Interest for her/him. We are interested in finding a user-specific balance of compatibility and interest within a recommendation model that integrates heterogeneous evaluation criteria to appropriately take these aspects into account. We tested our model on both ASD and "neurotypical" people. The evaluation results show that, on both groups, our model outperforms in accuracy and ranking capability the recommender systems based on item compatibility, on user preferences, or which integrate these two aspects by means of a uniform evaluation model.

Using consumer feedback from location-based services in PoI recommender systems for people with autism

“…These factors hamper both the acquisition of information about individual properties of users, and the execution of massive tests to evaluate the systems targeted to them. For our work, we employ a dataset that was collected by Mauro et al (2020). We gathered data by means of a questionnaire in which we asked participants to rate in the [1,5] Likert scale the following variables:…”

“…This section presents the lower level of the framework for the compatibilityaware recommendation of places shown in Figure 1. This portion of the framework is based on the work by (Mauro et al, 2020) and we outline it to make the present paper self-contained. Table 6 shows the notation we use.…”

“…This is crucial because what bothers people with autism has great importance in their daily choices and can determine a high level of stress and anxiety (Simm et al, 2016). Mauro et al (2020Mauro et al ( , 2022 propose to distinguish the role of user preferences and compatibility in PoI suggestion. The idea is to estimate the suitability of a place p for a user u by evaluating how much u is expected to like p, and how compatible p is with u, depending on u's sensory aversions.…”

Beyond Traditional Cultural Heritage Recommender Systems: Suggesting Airbnb Experiences to Users

“…Personalized travel guides, such as those described in [6,7,20], suggest places and/or events by analyzing the user's interests in item categories (e.g., cinemas or parks), as well as her/his preferences for specific item features, such as the types of artwork exposed in a museum. Moreover, some inclusive recommender systems, like PIUMA [8,23] and INTRIGUE [3], examine sensory or accessibility features of items to guarantee that the user can smoothly experience the suggested places. In all such cases, the only evaluated entity is the item itself, whose features are matched to the preferences of the target user in order to estimate its suitability.…”

NearMe: Dynamic Exploration of Geographical Areas

“…Personalized mobile guides, such as [7,2,10,22], help people find PoIs relevant to their interests. They also present detailed information about places.…”