Addressing the Cold Start with Positive-Only Feedback Through Semantic-Based Recommendations

2017 ◽  
Vol 25 (Suppl. 2) ◽  
pp. 57-78 ◽  
Author(s):  
Paolo Tomeo ◽  
Ignacio Fernández-Tobías ◽  
Iván Cantador ◽  
Tommaso Di Noia
Keyword(s):  
Cold Start ◽  
User Preferences ◽  
Evaluation Methodology ◽  
Quality Factors ◽  
Rigorous Evaluation ◽  
Semantic Metadata ◽  
Hybrid Approaches ◽  
Data User ◽  
Recommendation Accuracy ◽  
Hybrid Recommendation

Recommender systems aim to provide users with accurate item suggestions in a personalized fashion, but struggle in the case of cold start users, for whom there is a scarcity of preference data. User preferences can be either explicitly stated by the users — often by means of ratings —, or implicitly acquired by a system — for instance by mining text reviews, search queries, and purchase records. Recommendation methods have been mostly designed to deal with numerical ratings. However, real scenarios with user preferences expressed in the form of binary and unary (positive-only) feedback, e.g. the thumbs up/down in YouTube, and the likes in Facebook, are increasingly popular, and make the user cold start problem even more challenging. To address the cold start with positive-only feedback situations, we propose to exploit data additional to user preferences by means of specialized hybrid recommendation methods. In particular, we investigate a number of graph-based and matrix factorization recommendation models that jointly exploit user preferences and item semantic metadata automatically extracted from the well-known knowledge graph of DBpedia. Following a rigorous evaluation methodology for cold start, we empirically compare the above hybrid recommendation models on a Facebook dataset containing users likes for items in three different domains, namely books, movies and music. The achieved experimental results show that the semantics-aware hybrid approaches we propose outperform content-based and collaborative filtering baselines. In addition to recommendation accuracy, in our evaluation we also consider individual and aggregate diversity of recommendations as key quality factors in the users’ satisfaction.

scholarly journals Accuracy improvements for cold-start recommendation problem using indirect relations in social networks

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Fu Jie Tey ◽  
Tin-Yu Wu ◽  
Chiao-Ling Lin ◽  
Jiann-Liang Chen
Keyword(s):  
Social Media ◽  
Recommender System ◽  
Mobile Networks ◽  
Reference Value ◽  
User Preferences ◽  
Digital Information ◽  
Internet Applications ◽  
Social Media Networks ◽  
Recommendation Accuracy ◽  
Gain Access

AbstractRecent advances in Internet applications have facilitated information spreading and, thanks to a wide variety of mobile devices and the burgeoning 5G networks, users easily and quickly gain access to information. Great amounts of digital information moreover have contributed to the emergence of recommender systems that help to filter information. When the rise of mobile networks has pushed forward the growth of social media networks and users get used to posting whatever they do and wherever they visit on the Web, such quick social media updates already make it difficult for users to find historical data. For this reason, this paper presents a social network-based recommender system. Our purpose is to build a user-centered recommender system to exclude the products that users are disinterested in according to user preferences and their friends' shopping experiences so as to make recommendations effective. Since there might be no corresponding reference value for new products or services, we use indirect relations between friends and “friends’ friends” as well as sentinel friends to improve the recommendation accuracy. The simulation result has proven that our proposed mechanism is efficient in enhancing recommendation accuracy.

Modelling trust networks using resistive circuits for trust-aware recommender systems

2016 ◽  
Vol 43 (1) ◽  
pp. 135-144 ◽  
Author(s):  
Mehdi Hosseinzadeh Aghdam ◽  
Morteza Analoui ◽  
Peyman Kabiri
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Cold Start ◽  
User Preferences ◽  
Item Selection ◽  
Trust Networks ◽  
Trust Inference ◽  
Trust Information

Recommender systems have been widely used for predicting unknown ratings. Collaborative filtering as a recommendation technique uses known ratings for predicting user preferences in the item selection. However, current collaborative filtering methods cannot distinguish malicious users from unknown users. Also, they have serious drawbacks in generating ratings for cold-start users. Trust networks among recommender systems have been proved beneficial to improve the quality and number of predictions. This paper proposes an improved trust-aware recommender system that uses resistive circuits for trust inference. This method uses trust information to produce personalized recommendations. The result of evaluating the proposed method on Epinions dataset shows that this method can significantly improve the accuracy of recommender systems while not reducing the coverage of recommender systems.

scholarly journals Preference Mining Using Neighborhood Rough Set Model on Two Universes

2016 ◽  
Vol 2016 ◽  
pp. 1-13 ◽  
Author(s):  
Kai Zeng
Keyword(s):  
Rough Set ◽  
User Satisfaction ◽  
Traditional Method ◽  
Cold Start ◽  
Effective Solution ◽  
Neighborhood Rough Set ◽  
Recommendation Accuracy ◽  
Item Data ◽  
Two Universes ◽  
Cold Start Problem

Preference mining plays an important role in e-commerce and video websites for enhancing user satisfaction and loyalty. Some classical methods are not available for the cold-start problem when the user or the item is new. In this paper, we propose a new model, called parametric neighborhood rough set on two universes (NRSTU), to describe the user and item data structures. Furthermore, the neighborhood lower approximation operator is used for defining the preference rules. Then, we provide the means for recommending items to users by using these rules. Finally, we give an experimental example to show the details of NRSTU-based preference mining for cold-start problem. The parameters of the model are also discussed. The experimental results show that the proposed method presents an effective solution for preference mining. In particular, NRSTU improves the recommendation accuracy by about 19% compared to the traditional method.

scholarly journals Multi-Feature Discrete Collaborative Filtering for Fast Cold-Start Recommendation

2020 ◽  
Vol 34 (01) ◽  
pp. 270-278
Author(s):  
Yang Xu ◽  
Lei Zhu ◽  
Zhiyong Cheng ◽  
Jingjing Li ◽  
Jiande Sun
Keyword(s):  
Collaborative Filtering ◽  
Large Scale ◽  
Feature Fusion ◽  
Computation Time ◽  
Cold Start ◽  
User Preferences ◽  
Low Rank ◽  
Specific Content ◽  
Hash Codes ◽  
Content Feature

Hashing is an effective technique to address the large-scale recommendation problem, due to its high computation and storage efficiency on calculating the user preferences on items. However, existing hashing-based recommendation methods still suffer from two important problems: 1) Their recommendation process mainly relies on the user-item interactions and single specific content feature. When the interaction history or the content feature is unavailable (the cold-start problem), their performance will be seriously deteriorated. 2) Existing methods learn the hash codes with relaxed optimization or adopt discrete coordinate descent to directly solve binary hash codes, which results in significant quantization loss or consumes considerable computation time. In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF), to solve these problems. Specifically, a low-rank self-weighted multi-feature fusion module is designed to adaptively project the multiple content features into binary yet informative hash codes by fully exploiting their complementarity. Additionally, we develop a fast discrete optimization algorithm to directly compute the binary hash codes with simple operations. Experiments on two public recommendation datasets demonstrate that MFDCF outperforms the state-of-the-arts on various aspects.

Social Recommendation Combining Trust Relationship and Distance Metric Factorization

2020 ◽  
Vol 29 (15) ◽  
pp. 2050249
Author(s):  
Ming Ye ◽  
Yuanle Deng
Keyword(s):  
Social Relations ◽  
Recommender System ◽  
Cold Start ◽  
User Preferences ◽  
Dijkstra Algorithm ◽  
Distance Metric ◽  
Social Recommendation ◽  
Trust Relationship ◽  
Potential Factor ◽  
The One

The recommender system predicts user preferences by mining user historical behavior data. This paper proposes a social recommendation combining trust relationship and distance metric factorization. On the one hand, the recommender system has a cold start problem, which can be effectively alleviated by adding social relations. Simultaneously, to improve the problem of sparse trust matrix, we use the Jaccard similarity coefficient and the Dijkstra algorithm to reconstruct the trust matrix and explore the potential user trust relationship. On the other hand, the traditional matrix factorization algorithm is modeled by the user item potential factor dot product, however, it does not satisfy the triangle inequality property and affects the final recommender effect. The primary motivator behind our approach is to combine the best of both worlds, mitigate the inherent weaknesses of each paradigm. Combining the advantages of the two ideas, it has been demonstrated that our algorithm can enhance recommender performance and improve cold start in recommender systems.

scholarly journals An Efficient and Intelligent Recommender System for Mobile Platform

2018 ◽  
Vol 37 (4) ◽  
pp. 463-480
Author(s):  
Muhammad Jabbar ◽  
Qaisar Javaid ◽  
Muhammad Arif ◽  
Asim Munir ◽  
Ali Javed
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Past History ◽  
Subjective Evaluation ◽  
Mobile Platform ◽  
Value Addition ◽  
Hybrid Scheme ◽  
Hybrid Approaches ◽  
User Ratings ◽  
Hybrid Recommendation

Recommender Systems are valuable tools to deal with the problem of overloaded information faced by most of the users in case of making purchase decision to buy any item. Recommender systems are used to provide recommendations in many domains such as movies, books, digital equipment’s, etc. The massive collection of available books online presents a great challenge for users to select the relevant books that meet their preferences. Users usually read few pages or contents to decide whether to buy a certain book or not. Recommender systems provide different value addition factors such as similar user ratings, users past history, user profiles, etc. to facilitate the users in terms of providing relevant recommendations according to their preferences. Recommender systems are broadly categorized into content based approach and collaborative filtering approach. Content based or collaborative filtering approaches alone are not sufficient to provide most accurate and relevant recommendations under diverse scenarios. Therefore, hybrid approaches are also designed by combining the features of both the content based and collaborative filtering approaches to provide more relevant recommendations. This paper proposes an efficient hybrid recommendation scheme for mobile platform that includes the traits of content based and collaborative filtering approaches in addition of the context based approach that is included to provide the latest books recommendations to user.Objective and subjective evaluation measures are used to compute the performance of the proposed system. Experimental results are promising and signify the effectiveness of our proposed hybrid scheme in terms of most relevant and latest books recommendations.

scholarly journals Global Multi-Source Information Fusion Management and Deep Learning Optimization for Tourism

2022 ◽  
Vol 34 (3) ◽  
pp. 1-21
Author(s):  
Xue Yu
Keyword(s):  
Recommendation System ◽  
Latent Dirichlet Allocation ◽  
Target Location ◽  
Geographical Location ◽  
Cold Start ◽  
User Preferences ◽  
Personalized Recommendation ◽  
Interest Point ◽  
Source Information ◽  
Interest Points

The purpose is to solve the problems of sparse data information, low recommendation precision and recall rate and cold start of the current tourism personalized recommendation system. First, a context based personalized recommendation model (CPRM) is established by using the labeled-LDA (Labeled Latent Dirichlet Allocation) algorithm. The precision and recall of interest point recommendation are improved by mining the context information in unstructured text. Then, the interest point recommendation framework based on convolutional neural network (IPRC) is established. The semantic and emotional information in the comment text is extracted to identify user preferences, and the score of interest points in the target location is predicted combined with the influence factors of geographical location. Finally, real datasets are adopted to evaluate the recommendation precision and recall of the above two models and their performance of solving the cold start problem.

scholarly journals MFNP: A Meta-optimized Model for Few-shot Next POI Recommendation

2021 ◽  
Author(s):  
Huimin Sun ◽  
Jiajie Xu ◽  
Kai Zheng ◽  
Pengpeng Zhao ◽  
Pingfu Chao ◽  
...  
Keyword(s):  
State Of The Art ◽  
Cold Start ◽  
User Preferences ◽  
Location Based Services ◽  
Point Of Interest ◽  
Poi Recommendation ◽  
Meta Learning ◽  
Optimized Model ◽  
Real World Datasets ◽  
Cold Start Problem

Next Point-of-Interest (POI) recommendation is of great value for location-based services. Existing solutions mainly rely on extensive observed data and are brittle to users with few interactions. Unfortunately, the problem of few-shot next POI recommendation has not been well studied yet. In this paper, we propose a novel meta-optimized model MFNP, which can rapidly adapt to users with few check-in records. Towards the cold-start problem, it seamlessly integrates carefully designed user-specific and region-specific tasks in meta-learning, such that region-aware user preferences can be captured via a rational fusion of region-independent personal preferences and region-dependent crowd preferences. In modelling region-dependent crowd preferences, a cluster-based adaptive network is adopted to capture shared preferences from similar users for knowledge transfer. Experimental results on two real-world datasets show that our model outperforms the state-of-the-art methods on next POI recommendation for cold-start users.

On the End-to-End Development of a Cultural Tourism Recommender

2019 ◽  
Vol 3 (2) ◽  
pp. 73-90
Author(s):  
George P. Pavlidis
Keyword(s):  
Cultural Heritage ◽  
Collaborative Filtering ◽  
Information Overload ◽  
Cultural Tourism ◽  
User Preferences ◽  
Regional Economies ◽  
Knowledge Based ◽  
Hybrid Approaches ◽  
Main Target ◽  
End To End

Recommenders are systems that employ some knowledge on items and user preferences, along with sophisticated algorithms to provide personalised content and services. They have been around to tackle the information overload and personalisation demand in today's always-connected world. This technology appeared in the cultural heritage domain relatively recently, but the bibliography is already rich, as cultural tourism plays an important role for regional economies. From the technical perspective, different approaches, like collaborative filtering, content-based, knowledge-based and hybrid approaches, have been adopted. From the intuition perspective, the approaches are influenced by current conceptualisation and specific application domains and demands. The museum has been one of the main target applications, either as a part of visit support or in the context of cultural tourism initiatives. This article presents a review of the domain and draws a generic blueprint for the end-to-end development of a recommender for cultural tourism that outperforms a baseline popularity-based approach.

Sign in / Sign up

Export Citation Format

Share Document