Content-aware point-of-interest recommendation based on convolutional neural network (original) (raw)
Related papers
Spatial-Aware Hierarchical Collaborative Deep Learning for POI Recommendation
IEEE Transactions on Knowledge and Data Engineering, 2017
Point-of-interest (POI) recommendation has become an important way to help people discover attractive and interesting places, especially when they travel out of town. However, the extreme sparsity of user-POI matrix and cold-start issues severely hinder the performance of collaborative filtering-based methods. Moreover, user preferences may vary dramatically with respect to the geographical regions due to different urban compositions and cultures. To address these challenges, we stand on recent advances in deep learning and propose a Spatial-Aware Hierarchical Collaborative Deep Learning model (SH-CDL). The model jointly performs deep representation learning for POIs from heterogeneous features and hierarchically additive representation learning for spatial-aware personal preferences. To combat data sparsity in spatial-aware user preference modeling, both the collective preferences of the public in a given target region and the personal preferences of the user in adjacent regions are exploited in the form of social regularization and spatial smoothing. To deal with the multimodal heterogeneous features of the POIs, we introduce a late feature fusion strategy into our SH-CDL model. The extensive experimental analysis shows that our proposed model outperforms the state-of-the-art recommendation models, especially in out-of-town and cold-start recommendation scenarios.
Learning Graph-based POI Embedding for Location-based Recommendation
Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, 2016
With the rapid prevalence of smart mobile devices and the dramatic proliferation of location-based social networks (LB-SNs), location-based recommendation has become an important means to help people discover attractive and interesting points of interest (POIs). However, extreme sparsity of user-POI matrix and cold-start issue create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Moreover, locationbased recommendation requires spatiotemporal context awareness and dynamic tracking of the user's latest preferences in a real-time manner. To address these challenges, we stand on recent advances in embedding learning techniques and propose a generic graphbased embedding model, called GE, in this paper. GE jointly captures the sequential effect, geographical influence, temporal cyclic effect and semantic effect in a unified way by embedding the four corresponding relational graphs (POI-POI, POI-Region, POI-Time and POI-Word) into a shared low dimensional space. Then, to support real-time recommendation, we develop a novel time-decay method to dynamically compute the user's latest preferences based on the embedding of his/her checked-in POIs learnt in the latent space. We conduct extensive experiments to evaluate the performance of our model on two real large-scale datasets, and the experimental results show its superiority over other competitors, especially in recommending cold-start POIs. Besides, we study the contribution of each factor to improve location-based recommendation, and find that both sequential effect and temporal cyclic effect play more important roles than geographical influence and semantic effect.
Location-Aware Personalized News Recommendation with Deep Neural Network
Recently attractiveness of cell phones also rapid development of the mobile web increases, clients would now be able see the news feed whenever they need; along these lines, their news partialities are usually identified with users geographical circumstances. Thus, there are numerous researches focus on location aware news recommendation techniques, which recommends the clients news happening closest to them. However, in a real world, clients' news recommendations are not just associated with their locations, yet in addition strongly identified with their own interests. This system propose a hybrid strategy called location aware customized news recommendations with explicit semantic analysis, which prescribes news utilizing both the clients' personal interests and their topographical contexts. In any case, the Wikipedia based theme space in LP-ESA experiences the issues of high dimensionality, sparsity, and redundancy, which incredibly degrade the execution of LP-ESA. For tackling this problem, here proposed a LP-DSA for exploiting recommendation oriented deep neural system for removing dense, abstract, low dimensional and effective feature representations for users, news and locations.
ISPRS International Journal of Geo-Information, 2020
Travel location recommendation methods using community-contributed geotagged photos are based on past check-ins. Therefore, these methods cannot effectively work for new travel locations, i.e., they suffer from the travel location cold start problem. In this study, we propose a convolutional neural network and matrix factorization-based travel location recommendation method to address the problem. Specifically, a weighted matrix factorization method is used to obtain the latent factor representations of travel locations. The latent factor representation for a new travel location is estimated from its photos by using a convolutional neural network. Experimental results on a Flickr dataset demonstrate that the proposed method can provide better recommendations than existing methods.
2018
Point-of-interest recommendation has become an important way to help people discover attractive and interesting places, especially when they travel out of town. User performance may very important with respect to the geographical reason with different urban area cultures, environment. For solving these all issue I have to propose deep learning and proposed a special aware hierarchical collaborative deep learning algorithm. In this model jointly perform deep representation learning for point of interest from heterogeneous feature and hierarchical additive information learning from special aware individual performance. the collective preferences of the public in a given target regionand the personal preferences of the user in adjacent regions are exploited in the form of social regularization and spatial smoothing. To deal with the multimodal heterogeneous features of the point of interests, we introduce a late feature fusion strategy into our special aware hierarchical collaborative ...
IJERT-Efficient and Effective Location Recommendation through Content Analysis
International Journal of Engineering Research and Technology (IJERT), 2020
https://www.ijert.org/efficient-and-effective-location-recommendation-through-content-analysis https://www.ijert.org/research/efficient-and-effective-location-recommendation-through-content-analysis-IJERTCONV8IS08007.pdf Location recommendation plays a vital role in helping people in finding beautiful places. The recent research has studied how to recommend locations with social and geographical information, but few of them addressed the cold-start problem. A typical method is to feed them into explicit-feedback-based content-aware collaborative filtering, but they require drawing negative samples for better learning performance, as users' negative preference is not observable in human mobility. Prior studies have empirically shown sampling-based methods do not perform well. Therefore, a novel approach has been implemented which recommend location based on machine learning process. The user reviews are taken into consideration as dataset. Dataset are preprocessed and meaning of user reviews is understood by system automatically through NLP. Then new recommendation has been suggested through this process and data base is loaded. Hence our system achieves more accurate recommendation compared to other existing approach. Finally, we evaluate LR-NLP with a user review dataset in which users have profiles and textual content. The results show that our proposed outperforms several competing baselines, and that user feedback is not only effective for improving recommendations but also overcomes cold-start problems.
Group-Based Recurrent Neural Networks for POI Recommendation
ACM/IMS Transactions on Data Science, 2020
With the development of mobile Internet, many location-based services have accumulated a large amount of data that can be used for point-of-interest (POI) recommendation. However, there are still challenges in developing an unified framework to incorporate multiple factors associated with both POIs and users due to the heterogeneity and implicity of this information. To alleviate the problem, this work proposes a novel group-based method for POI recommendation jointly considering the reviews, categories, and geographical locations, called the Group-based Temporal Sentiment-Aspect-Region Recurrent Neural Network (GTSAR-RNN). We divide the users into different groups and then train an individual RNN for each group with the goal of improving its pertinence. In GTSAR-RNN, we consider not only the effects of temporal and geographical contexts but also the users’ sentimental opinions on locations. Experimental results show that GTSAR-RNN acquires significant improvements over the baseline...
Location Embeddings for Next Trip Recommendation
2019
The amount of information available in social media and specialized blogs has become useful for a user to plan a trip. However, the user is quickly overwhelmed by the list of possibilities offered to him, making his search complex and time-consuming. Recommender systems aim to provide personalized suggestions to users by leveraging different type of information, thus assisting them in their decision-making process. Recently, the use of neural networks and knowledge graphs have proven to be efficient for items recommendation. In our work, we propose an approach that leverages contextual, collaborative and content information in order to recommend personalized destinations to travelers. We compare our approach with a set of state of the art collaborative filtering methods and deep learning based recommender systems.
Point-of-Interest Recommender Systems: A Survey from an Experimental Perspective
ACM Computing Surveys, 2021
Point-of-Interest recommendation is an increasing research and developing area within the widely adopted technologies known as Recommender Systems. Among them, those that exploit information coming from Location-Based Social Networks (LBSNs) are very popular nowadays and could work with different information sources, which pose several challenges and research questions to the community as a whole. We present a systematic review focused on the research done in the last 10 years about this topic. We discuss and categorize the algorithms and evaluation methodologies used in these works and point out the opportunities and challenges that remain open in the field. More specifically, we report the leading recommendation techniques and information sources that have been exploited more often (such as the geographical signal and deep learning approaches) while we also alert about the lack of reproducibility in the field that may hinder real performance improvements. CCS Concepts: • Information systems → Retrieval models and ranking; Recommender systems; Retrieval effectiveness.
Clustering-based Location Authority Deep Model in the Next Point-of-Interest Recommendation
IEEE/WIC/ACM International Conference on Web Intelligence, 2021
With the development of location-based social networks (LBSNs), sequential Point-of-Interest (POI) recommendation is getting more and more vitality. Current sequential POI recommendation models predict user's future mobility based on user's previous behaviors without considering the effect of the significant location (i.e. location authority). Besides, it is hard to effectively capture user interests because of the data sparsity problem in the LBSNs dataset. To this end, we propose a clustering-based location authority deep model (CLADM) that integrates POI clusters and location authority to reduce the scale of POI candidate set to alleviate the issue of data sparsity. In the proposed model, we present two encoders based on the attention mechanism: the first encoder is an additive attention encoder to exploit user preferences on POI clusters, and the second encoder mines user preferences of POIs. Considering that the user check-in data is the implicit feedback, we design a binary self-attention layer in the second encoder with a sigmoid function. We adopt two real-world LBSNs datasets with different scales to evaluate our model. The experimental results show that our proposed model greatly outperforms the state-of-the-art methods for sequential POI recommendation.