Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/29889
Title: Extracting user preferences and personality from text for restaurant recommendation
Authors: Christodoulou, Evripides 
Gregoriades, Andreas 
Herodotou, Herodotos 
Pampaka, Maria 
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Keywords: Consumer Personality;Food preference extraction;Recommender System;Topic Modelling
Issue Date: 23-Sep-2022
Source: 5th Workshop on Online Recommender Systems and User Modeling, ORSUM 2022, Seattle, 23 September 2022
Volume: 3303
Conference: CEUR Workshop Proceedings 
Abstract: Restaurant recommender systems are designed to support restaurant selection by assisting consumers with the information overload problem. However, despite their promises, they have been criticized of insufficient performance. Recent research in recommender systems has acknowledged the importance of personality in improving recommendation; however, limited work exploited this aspect in the restaurant domain. Similarly, the importance of user preferences in food has been known to improve recommendation but most systems explicitly ask the users for this information. In this paper, we explore the influence of personality and user preference by utilizing text in consumers’ electronic word of mouth (eWOM) to predict the probability of a user enjoying a restaurant he/she had not visited before. Food preferences are extracted though a trained named-entity recognizer learned from a labelled dataset of foods, generated using a rule-based approach. The prediction of user personality is achieved through a bi-directional transformer approach with a feed-forward classification layer, due to its improved performance in similar problems over other machine learning models. The personality classification model utilizes the textual information of reviews and predicts the personality of the author. Topic modelling is used to identify additional features that characterize users’ preferences and restaurants properties. All aforementioned features are used collectively to train an extreme gradient boosting tree model, which outputs the predicted user rating of restaurants. The trained model is compared against popular recommendation techniques such as nonnegative matrix factorization and single value decomposition.
URI: https://hdl.handle.net/20.500.14279/29889
ISSN: 16130073
Rights: © Elsevier B.V.
Type: Conference Papers
Affiliation : Cyprus University of Technology 
University of Manchester 
Appears in Collections:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation

CORE Recommender
Show full item record

Page view(s) 20

155
Last Week
0
Last month
2
checked on Nov 6, 2024

Google ScholarTM

Check


This item is licensed under a Creative Commons License Creative Commons