R-Rec: A rule-based system for contextual suggestion using tag-description similarity

TL;DR

This paper introduces R-Rec, a rule-based system that recommends points-of-interest by analyzing user preferences through tag-description similarity, effectively personalizing suggestions based on past likes and dislikes.

Contribution

The paper presents a novel rule-based approach for contextual suggestion that leverages tag-description similarity to improve recommendation accuracy.

Findings

Effective ranking of suggestions based on user preferences

Improved recommendation accuracy demonstrated on TREC dataset

Utilizes tag and description similarity for personalization

Abstract

Contextual Suggestion deals with search techniques for complex information needs that are highly focused on context and user needs. In this paper, we propose \emph{R-Rec}, a novel rule-based technique to identify and recommend appropriate points-of-interest to a user given her past preferences. We try to embody the information that the user shares in the form of rating and tags of any previous point(s)-of-interest and use it to rank the unrated candidate suggestions. The ranking function is computed based on the similarity between a suggestion and the places that the user like and the dissimilarity between the suggestion and the places disliked by the user. Experiments carried out on TREC-Contextual Suggestion 2015 dataset reveal the efficacy of our method.