Research Area:  Machine Learning

Abstract:

Conversational Recommendation Systems (CRSs) are multi-turn dialogue softwares that support recommendation goals. Having a CRS that generates personalized recommendations for its users is one of the challenging topics in the recommendation research field. This is due to the diversity of preferences that a user might have within a recommendation session. Recent CRS frameworks are still not really able to effectively provide items of interest to their users, as they do not consider the individuals personality traits during the recommendation process. These traits are the enduring characteristics and behaviors that comprise a persons unique adjustment and distinguish him from other persons. Thus, considering them during the recommendation process could significantly boost the model performance. In this paper, we propose a personality-aware and prompt-based CRS framework named PPPG-DialoGPT “A Personality and Preference-aware Prompt-based Goal-oriented DialoGPT model”. Our proposed approach aims to benefit from the significant impact that personality traits and prompt-based learning frameworks have on improving the performance of different Natural Language Processing (NLP) and one-shot recommendation tasks. To the best of our knowledge, this paper is the first to employ both individual personality traits and prompts templates during a dialogue-based recommendation session in the field of conversational recommendation system. Experiments and results show that the use of the users personality traits leads to an improvement in the performance of both recommendation and response generation tasks on the movie-based TG- Redial dataset.

Keywords:  
Conversational Recommendation Systems
Goal-oriented DialoGPT
Natural Language Processing
TG- Redial dataset

Author(s) Name:  Fahed Elourajini Université de Montréal, Montreal, Canada , Esma Aïrncur

Publisher name:  IEEE

DOI:  https://doi.org/10.1109/WI-IAT59888.2023.00044

Volume Information:  -

Paper Link:   https://ieeexplore.ieee.org/abstract/document/10350184