Effective neural architectures for context-aware venue recommendation

Manotumruksa, Jarana (2019) Effective neural architectures for context-aware venue recommendation. PhD thesis, University of Glasgow.

Full text available as:
[img]
Preview
PDF
Download (7MB) | Preview

Abstract

Users in Location-Based Social Networks (LBSNs), such as Yelp and Foursquare, can search for interesting venues such as restaurants and museums to visit, or share their location with their friends by making an implicit feedback (e.g. checking in at venues they have visited). The users can also leave explicit feedback on the venues they have visited by providing rat- ings and/or comments. Such explicit and implicit feedback by the users provide rich infor- mation about both users and venues, and thus can be leveraged to study the users’ movement in urban cities, as well as enhance the quality of personalised venue recommendations. Un- like traditional recommendation systems (e.g. book and movie recommendation systems), making effective venue recommendations is more challenging because we need to take into account the users’ current context (e.g. time of the day, user’s current location as well as his recently visited venues).
Two common techniques that are widely used in the literature for venue recommen- dation systems are Matrix Factorisation (MF) and Bayesian Personalised Ranking (BPR). MF is a popular Collaborative Filtering (CF) technique that can leverage the users’ explicit feedback (e.g. the numerical ratings) to predict the users’ ratings on the venues and hence relevant venues can be suggested to the users based on these predicted ratings. On the other hand, BPR is a pairwise ranking-based model that can leverage implicit feedback to generate effective top-K venue recommendations. In this thesis, based upon MF and BPR models, we aim to generate effective context-aware venue recommendation that a user may wish to visit based on the user’s historical explicit and implicit feedbacks, the user’s contextual informa- tion (e.g. the user’s current location and time of the day) and additional information (e.g. the geographical location of venues and users’ social relationships). To achieve this goal, we need to address the following challenges: namely (C1) modelling the users’ preferences and the characteristic of venues, (C2) capturing the complex structure of user-venue inter- actions in a Collaborative Filtering manner, (C3) modelling the users’ short-term (dynamic) preferences from the sequential order of user’s observed feedback as well as the contextual information associated with the successive feedback, (C4) generating accurate top-K venue recommendations based on the users’ preferences using a pairwise ranking-based model and (C5) appropriately sampling potential negative instances to train a ranking-based model.
First, to address challenge C1, we leverage the users’ explicit feedback (e.g. their rat- ings and the textual content of the comments) and additional information (e.g. users’ social relationships) to effectively model the users’ preferences and the characteristics of venues. In particular, we propose a novel regularisation technique and a factorisation-based model that leverages the users’ explicit feedback and the additional information to improve the rat- ing prediction accuracy of the traditional MF model. Experiments conducted on a large scale rating dataset on LBSN demonstrate that the textual content of comments plays an important role in enhancing the accuracy of rating prediction.
Second, we investigate how to leverage the users’ implicit feedback and additional in- formation such as the users’ social relationship and the geographical location of venues to improve the quality of top-K venue recommendations. We argue that the potential negative instances can be effectively sampled based on the social correlations between users and their friends as well as the geographical influences between the users’ and venues’ geographi- cal location. In particular, to address challenges C4 and C5, we propose a novel pairwise ranking-based framework for top-K venue recommendations that can incorporate multiple sources of additional information (e.g. the users’ social relationship and the geographical location of venues) to effectively sample the potential negative instances. Experimental re- sults on three large scale checkin and rating datasets from LBSNs demonstrate that the social correlations and the geographical influences play an important role to the quality of sampled negative instances and hence can improve the quality of top-K venue recommendations.
Finally, to address challenges C2 and C3, we propose a framework for context-aware venue recommendations that exploits Deep Neural Network (DNN) models to effectively capture the complex structure of user-venue interactions and the users’ long-term (dynamic) preferences from their sequential order of checkins. In particular, within the framework, we propose a novel Recurrent Neural Network (RNN) architecture that can effectively in- corporate the contextual information associated with the successive implicit feedback (e.g. the time interval and the geographical distance between two successive checkins) to gener- ate high quality context-aware venue recommendations. Experimental results on three large scale checkin and rating datasets from LBSNs demonstrate the effectiveness and robustness of our proposed framework for context-aware venue recommendations. In particular, the results demonstrate that the sequential order of users’ implicit feedback can be leveraged to effectively improve the effectiveness of context-aware venue recommendation system. In addition, the time intervals and the geographical distances between two successive checkins play an important role in capturing the users’ short-term preferences.

Item Type: Thesis (PhD)
Qualification Level: Doctoral
Keywords: Recommendation system, deep neural network, location-based social network.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Colleges/Schools: College of Science and Engineering > School of Computing Science
Supervisor's Name: Macdonald, Dr. Craig and Ounis, Professor Iadh
Date of Award: 2019
Depositing User: Mr Jarana Manotumruksa
Unique ID: glathesis:2019-76735
Copyright: Copyright of this thesis is held by the author.
Date Deposited: 03 Dec 2019 14:45
Last Modified: 05 Mar 2020 21:49
Thesis DOI: 10.5525/gla.thesis.76735
URI: http://theses.gla.ac.uk/id/eprint/76735
Related URLs:

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year