CARAN: A Context-Aware Recency-Based Attention Network for Point-of-Interest Recommendation

Abstract

Point-of-interest (POI) recommendation system that tries to anticipate user's next visiting location has attracted a plentiful research interest due to its ability in generating personalized suggestions. Since user's historical check-ins are sequential in nature, Recurrent neural network (RNN) based models with context embedding shows promising result for modeling user's mobility. However, such models can not provide correlation between non-consecutive and non-adjacent visits for understanding user's behavior. To mitigate data sparsity problem, many models use hierarchical gridding of the map which cannot represent spatial distance smoothly. Another important factor while providing POI recommendation is the impact of weather condition which has rarely been considered in the literature. To address the above shortcomings, we propose a Context-Aware Recency based Attention Network (CARAN) that incorporates weather condition with spatiotemporal context and gives focus on recently visited locations using the attention mechanism. It allows interaction between non-adjacent check-ins by using spatiotemporal matrices and uses linear interpolation for smooth representation of spatial distance. Moreover, we use positional encoding of the check-in sequence in order to maintain relative position of the visited locations. We evaluate our proposed model on three real world datasets and the result shows that CARAN surpasses the existing state-of-the art models by 7-14%.

Personalized POI Recommendation Using CAGRU and Implicit Semantic Feature Extraction in LBSN

“…To show the merits of the suggested personalized point-of-interest recommendation method, the transfer learning-based POI-recommendation method (Gupta & Bedathur, 2022), the CARAN method (Hossain et al, 2022), and GETNext (Yang et al, 2022) were compared with the proposed method under identical experimental conditions. The efficacy of each model's recommendations was assessed using Precision@K and Recall@K. To eliminate experimental result contingency, the recommended POI K numbers are 5, 10, and 15.…”

A recommender system-using novel deep network collaborative filtering

“…A bidirectional, gated network is suggested by the module for obtaining review text attributes. Bidirectional encoder representation from transformers (BERT) and an attention mechanism are used in the recurrent unit (Bi-GRU) text analysis method to assist the model choose the most important reviews [21], [22]. Construct a context-aware recency-based attention network (CARAN) that uses the attention mechanism to give recent visitation spots the highest priority based on the temporal and spatial context and the weather.…”

Long-Term Preference Mining With Temporal and Spatial Fusion for Point-of-Interest Recommendation

“…After proving their mantle in other fields, deep learning models like LSTM, CNN, attention network, and GRU have also been deployed in POI recommendations over the past years. Hossain et al [20] addressed the issue of nonconsecutiveness and non-adjacent visits in user behavior in their proposed framework CARAN that utilized an attention network to cater to the recency in the visits along with the weather conditions influence. The non-adjacent checkins and spatial distance consideration were monitored using spatiotemporal matrices, liner interpolation method, and positional encoding of check-in sequence.…”

“…Temporal content also holds critical weightage in recommendation tasks, representing both periodicity and asymmetry in check-in trajectory. Owing to the temporal aspect, the recency in the historical check-ins has also been exploited in [4], [5]. Semantic content has also been explored in combination with spatiotemporal data for user preference mining in several approaches.…”