Semantic Knowledge Discovery for User Profiling for Location-Based Recommender Systems
Abstract This paper introduces a purposed Location-based Recommender System (LBRS) that combines sentiment analysis and topic modelling techniques to improve user profiling for enhancing recommendations of Points of Interest (POIs). Using additional feature extraction, we built user profiles froma F...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer Nature
2021-07-01
|
Series: | Human-Centric Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.2991/hcis.k.210704.001 |
_version_ | 1797274407113064448 |
---|---|
author | Xiaohui Tao Nischal Sharma Patrick Delaney Aimin Hu |
author_facet | Xiaohui Tao Nischal Sharma Patrick Delaney Aimin Hu |
author_sort | Xiaohui Tao |
collection | DOAJ |
description | Abstract This paper introduces a purposed Location-based Recommender System (LBRS) that combines sentiment analysis and topic modelling techniques to improve user profiling for enhancing recommendations of Points of Interest (POIs). Using additional feature extraction, we built user profiles froma Foursquare dataset to evaluate our model and provide recommendations based on user opinions toward venues. Our combined model performed favourably against the baseline models, with an overall improved accuracy of 0.67. The limitations were the use of one dataset and that user profiles were constructed using predicted emotions extracted as features from review data with topic modelling, rather than literal user emotions. Nevertheless, this provides a step forward in user profile and emotion scoring, contributing further to the development of LBRS in the Tourism domain. |
first_indexed | 2024-03-07T14:57:53Z |
format | Article |
id | doaj.art-dd9f92449256408e971f658c8caa868a |
institution | Directory Open Access Journal |
issn | 2667-1336 |
language | English |
last_indexed | 2024-03-07T14:57:53Z |
publishDate | 2021-07-01 |
publisher | Springer Nature |
record_format | Article |
series | Human-Centric Intelligent Systems |
spelling | doaj.art-dd9f92449256408e971f658c8caa868a2024-03-05T19:20:40ZengSpringer NatureHuman-Centric Intelligent Systems2667-13362021-07-0111-2324210.2991/hcis.k.210704.001Semantic Knowledge Discovery for User Profiling for Location-Based Recommender SystemsXiaohui Tao0Nischal Sharma1Patrick Delaney2Aimin Hu3School of Sciences, University of Southern QueenslandSchool of Sciences, University of Southern QueenslandSchool of Sciences, University of Southern QueenslandGuilin Tourism UniversityAbstract This paper introduces a purposed Location-based Recommender System (LBRS) that combines sentiment analysis and topic modelling techniques to improve user profiling for enhancing recommendations of Points of Interest (POIs). Using additional feature extraction, we built user profiles froma Foursquare dataset to evaluate our model and provide recommendations based on user opinions toward venues. Our combined model performed favourably against the baseline models, with an overall improved accuracy of 0.67. The limitations were the use of one dataset and that user profiles were constructed using predicted emotions extracted as features from review data with topic modelling, rather than literal user emotions. Nevertheless, this provides a step forward in user profile and emotion scoring, contributing further to the development of LBRS in the Tourism domain.https://doi.org/10.2991/hcis.k.210704.001Location-based recommender systemFoursquaresentiment analysistopic modellingvenue recommendationplaces of interest |
spellingShingle | Xiaohui Tao Nischal Sharma Patrick Delaney Aimin Hu Semantic Knowledge Discovery for User Profiling for Location-Based Recommender Systems Human-Centric Intelligent Systems Location-based recommender system Foursquare sentiment analysis topic modelling venue recommendation places of interest |
title | Semantic Knowledge Discovery for User Profiling for Location-Based Recommender Systems |
title_full | Semantic Knowledge Discovery for User Profiling for Location-Based Recommender Systems |
title_fullStr | Semantic Knowledge Discovery for User Profiling for Location-Based Recommender Systems |
title_full_unstemmed | Semantic Knowledge Discovery for User Profiling for Location-Based Recommender Systems |
title_short | Semantic Knowledge Discovery for User Profiling for Location-Based Recommender Systems |
title_sort | semantic knowledge discovery for user profiling for location based recommender systems |
topic | Location-based recommender system Foursquare sentiment analysis topic modelling venue recommendation places of interest |
url | https://doi.org/10.2991/hcis.k.210704.001 |
work_keys_str_mv | AT xiaohuitao semanticknowledgediscoveryforuserprofilingforlocationbasedrecommendersystems AT nischalsharma semanticknowledgediscoveryforuserprofilingforlocationbasedrecommendersystems AT patrickdelaney semanticknowledgediscoveryforuserprofilingforlocationbasedrecommendersystems AT aiminhu semanticknowledgediscoveryforuserprofilingforlocationbasedrecommendersystems |