Context-Aware Explainable Recommendation Based on Domain Knowledge Graph

Abstract

With the rapid growth of internet data, knowledge graphs (KGs) are considered as efficient form of knowledge representation that captures the semantics of web objects. In recent years, reasoning over KG for various artificial intelligence tasks have received a great deal of research interest. Providing recommendations based on users’ natural language queries is an equally difficult undertaking. In this paper, we propose a novel, context-aware recommender system, based on domain KG, to respond to user-defined natural queries. The proposed recommender system consists of three stages. First, we generate incomplete triples from user queries, which are then segmented using logical conjunction (∧) and disjunction (∨) operations. Then, we generate candidates by utilizing a KGE-based framework (Query2Box) for reasoning over segmented logical triples, with ∧, ∨, and ∃ operators; finally, the generated candidates are re-ranked using neural collaborative filtering (NCF) model by exploiting contextual (auxiliary) information from GraphSAGE embedding. Our approach demonstrates to be simple, yet efficient, at providing explainable recommendations on user’s queries, while leveraging user-item contextual information. Furthermore, our framework has shown to be capable of handling logical complex queries by transforming them into a disjunctive normal form (DNF) of simple queries. In this work, we focus on the restaurant domain as an application domain and use the Yelp dataset to evaluate the system. Experiments demonstrate that the proposed recommender system generalizes well on candidate generation from logical queries and effectively re-ranks those candidates, compared to the matrix factorization model.

A Query Expansion Benchmark on Social Media Information Retrieval: Which Methodology Performs Best and Aligns with Semantics?

“…For instance, ontologies have been used to model event-related entities and relationships [28], while OWL ontologies were used to represent and organize entity-related information [29]. Semantic web technologies have also been used to support context-aware IR, personalized search, and recommendation systems [30]. In [31], unique query expansion techniques involve deriving a query's geographical footprint, accounting for spatial and non-spatial terms, the semantics of spatial relationships, and the context of use.…”

Explaining Recommendation System Using Counterfactual Textual Explanations

“…For example, Wang et al (2020) attempted to represent knowledge-graph paths with the semantic information of entities and their relations in order to make recommendations generated by the knowledge graph more explainable. Syed et al (2022) used first-order logic to generate triples from users' complex queries and then tried to find entities that satisfy these logical queries using a knowledge graph. These entities were sorted based on the information they captured from the context, and explanations were generated using the triples.…”

An Automatic Generation of Heterogeneous Knowledge Graph for Global Disease Support: A Demonstration of a Cancer Use Case

“…KGs provide additional features than ontologies as they provide real-world instances and data. KGs add extra information and real-world experiences enriching the basic concepts extracted from a specific domain of interest [23,24]. Ontology entity linking is the process of identifying and associating entities mentioned to a unique concept identifier that best represents it in an ontology [25][26][27][28].…”