Implicit User Feedback Research Articles

Enabling personalized VR experiences: a framework for real-time adaptation and recommendations in VR environments

The personalization of user experiences through recommendation systems has been extensively explored in Internet applications, but this has yet to be fully addressed in Virtual Reality (VR) environments. The complexity of managing geometric 3D data, computational load, and natural interactions poses significant challenges in real-time adaptation in these immersive experiences. However, tailoring VR environments to individual user needs and interests holds promise for enhancing user experiences. In this paper, we present Virtual Reality Environment Adaptation through Recommendations (VR-EAR), a framework designed to address this challenge. VR-EAR employs customizable object metadata and a hybrid recommendation system modeling implicit user feedback in VR environments. We utilize VR optimization techniques to ensure efficient performance. To evaluate our framework, we designed a virtual store where product locations dynamically adjust based on user interactions. Our results demonstrate the effectiveness of VR-EAR in adapting and personalizing VR environments in real time. domains.

A novel similarity measure SF-IPF for CBKNN with implicit feedback data

PurposeThe increasing popularity of music streaming services also increases the need to customize the services for each user to attract and retain customers. Most of the music streaming services will not have explicit ratings for songs; they will have only implicit feedback data, i.e user listening history. For efficient music recommendation, the preferences of the users have to be infered, which is a challenging task.Design/methodology/approachPreferences of the users can be identified from the users' listening history. In this paper, a hybrid music recommendation system is proposed that infers features from user's implicit feedback and uses the hybrid of content-based and collaborative filtering method to recommend songs. A Content Boosted K-Nearest Neighbours (CBKNN) filtering technique was proposed, which used the users' listening history, popularity of songs, song features, and songs of similar interested users for recommending songs. The song features are taken as content features. Song Frequency–Inverse Popularity Frequency (SF-IPF) metric is proposed to find the similarity among the neighbours in collaborative filtering. Million Song Dataset and Echo Nest Taste Profile Subset are used as data sets.FindingsThe proposed CBKNN technique with SF-IPF similarity measure to identify similar interest neighbours performs better than other machine learning techniques like linear regression, decision trees, random forest, support vector machines, XGboost and Adaboost. The performance of proposed SF-IPF was tested with other similarity metrics like Pearson and Cosine similarity measures, in which SF-IPF results in better performance.Originality/valueThis method was devised to infer the user preferences from the implicit feedback data and it is converted as rating preferences. The importance of adding content features with collaborative information is analysed in hybrid filtering. A new similarity metric SF-IPF is formulated to identify the similarity between the users in collaborative filtering.

Personalizing Activity Selection in Assistive Social Robots from Explicit and Implicit User Feedback

AbstractRobots in multi-user environments require adaptation to produce personalized interactions. In these scenarios, the user’s feedback leads the robots to learn from experiences and use this knowledge to generate adapted activities to the user’s preferences. However, preferences are user-specific and may suffer variations, so learning is required to personalize the robot’s actions to each user. Robots can obtain feedback in Human–Robot Interaction by asking users their opinion about the activity (explicit feedback) or estimating it from the interaction (implicit feedback). This paper presents a Reinforcement Learning framework for social robots to personalize activity selection using the preferences and feedback obtained from the users. This paper also studies the role of user feedback in learning, and it asks whether combining explicit and implicit user feedback produces better robot adaptive behavior than considering them separately. We evaluated the system with 24 participants in a long-term experiment where they were divided into three conditions: (i) adapting the activity selection using the explicit feedback that was obtained from asking the user how much they liked the activities; (ii) using the implicit feedback obtained from interaction metrics of each activity generated from the user’s actions; and (iii) combining explicit and implicit feedback. As we hypothesized, the results show that combining both feedback produces better adaptive values when correlating initial and final activity scores, overcoming the use of individual explicit and implicit feedback. We also found that the kind of user feedback does not affect the user’s engagement or the number of activities carried out during the experiment.

WeightedSLIM: A Novel Item-Weights Enriched Baseline Recommendation Model

This paper proposes a novel weight-enriched ranking-based baseline model, WeightedSLIM, aiming to provide more accurate top-N recommendations from implicit user feedback. The model utilizes ItemRank to calculate the ranking score of each item, which is then used as an item weight within the Sparse Linear Model (SLIM), while using Bayesian Personalized Ranking (BPR) to optimize the item similarity matrix. Experiments, conducted for performance comparison of the proposed model with existing recommendation models, demonstrate that it can indeed provide better recommendations and can be used as a strong baseline for top-N recommendations.

Research on personalized recommendation system for social media marketing content in big data environment

Abstract A personalized recommendation system is an effective and consistent marketing method that caters to consumer demand for goods. It solves the problem of consumer shopping choices on e-commerce websites and is currently a hot spot in the field of network information services. In this paper, from the perspective of the user’s shopping process, we summarize the four factors that can maximally reflect the consumer’s interest and preference, i.e., product browsing, collection, adding to cart, and purchasing behavior. To achieve static user interest weights, we quantify each index factor and set the corresponding rules. Considering the change in user interest, the decaying interest value over time is designed to compensate for the deficiencies of static system recommendations. We use implicit user feedback data to identify content that truly interests users and then construct a personalized recommendation algorithm for social media marketing content using multi-source data. The test results show that UIPR has an MRR value of more than 0.8 and an NDCG value of more than 0.55 in both the MovieLens and Taobao datasets, compared to the baseline model’s best value. This proves that UIPR consistently performs better and makes better recommendations.

익스플리싯 피드백 환경에서 추천 시스템을 위한 최신 지식증류기법들에 대한 성능 및 정확도 평가

Recommender systems provide users with the most favorable items by analyzing explicit or implicit feedback of users on items. Recently, as the size of deep-learning-based models employed in recommender systems has increased, many studies have focused on reducing inference time while maintaining high recommendation accuracy. As one of them, a study on recommender systems with a knowledge distillation (KD) technique is actively conducted. By KD, a small-sized model (i.e., student) is trained through knowledge extracted from a large-sized model (i.e., teacher), and then the trained student is used as a recommendation model. Existing studies on KD for recommender systems have been mainly performed only for implicit feedback settings. Thus, in this paper, we try to investigate the performance and accuracy when applied to explicit feedback settings. To this end, we leveraged a total of five state-of-the-art KD methods and three real-world datasets for recommender systems.

Recommending Words Using a Bayesian Network

Asset management involves the coordinated activities of an organisation to derive value from assets, which may include physical assets. It encompasses activities related to design, construction, installation, operation, maintenance, renewal, and asset disposal. Asset management ensures the coordination of all activities, resources, and data related to physical assets. Recording and monitoring all maintenance activities is a key part of asset management, often done using work orders (WOs). Technicians typically create WOs using “free text”, which can result in missing or ungrammatical words, making it difficult to identify trends and analyse information. To standardise the terminology used for the same asset maintenance operation, this paper proposes a method that suggests words to technicians as they complete WOs. The word suggestion algorithm is based on past maintenance records, and a Bayesian network-based recommender system adapts to present needs verified by technicians using implicit user feedback. Implementing this system aims to normalise the terms used by technicians when filling in a WO. The corpus for this work comes from asset management records collected in a health facility in Portugal operated by a private company.

Specifying requirements for collection and analysis of online user feedback.

According to data-driven Requirements Engineering (RE), explicit and implicit user feedback can be considered a relevant source of requirements, thus supporting requirements elicitation. However, limited attention has been paid so far to the role of online feedback in RE tasks, such as requirements validation, and on how to specify what online feedback to collect and analyse. We performed an action research study, together with a company that developed a platform for online training. This paper presents the design and execution of the study, and a discussion of its results. This study provides evidence about the need of practitioners to follow a simple but systematic approach for specifying requirements for data collection and analysis, at design time. Another outcome of this study is a method to tackle this task that leverages goal-oriented requirements modelling combined with Goal-Question-Metric. The applicability of the method has been explored on two industrial evaluations, while the perceived effectiveness, efficiency and acceptance have been assessed with practitioners through a dedicated survey.

Personalized Recommendation Algorithm of Tourist Attractions Based on Transfer Learning

With the development of information technology and the popularity of the Internet, the data on the network is growing exponentially. Information overload has become a significant issue for consumers seeking information. A recommendation system was created to detect users’ interests from huge amounts of data and to suit users’ specific information needs. Traditional collaborative filtering recommendation mostly uses scoring data for a recommendation, which has the problem of sparse data, which limits the performance of the recommendation system. On this basis, this paper studies the personalized recommendation algorithm of scenic spots with deep migration. Through the analysis of collaborative filtering recommendation methods, it is found that the traditional collaborative filtering methods only use scoring data for a recommendation, which has the problem of sparse data. Based on the vectorization of user interest, the similarity of user preference is calculated, and the matrix decomposition is carried out in cooperation with user implicit feedback, to integrate the knowledge transfer information into the matrix decomposition model, and make up for the lack of considering the attribute information of scenic spots in the matrix decomposition algorithm, and alleviate the problem of data sparsity. The findings of comparative trials suggest that the personalized scenic location recommendation approach proposed in this study, which is based on the depth migration algorithm, is effective. Compared with the benchmark recommendation method, the recommendation accuracy and recall rate has been improved to a certain extent.

Research on collaborative filtering based on user interest in the higher vocational e-commerce website development

E-commerce Recommender Systems suggest useful and interesting products to customers in order to increase user satisfaction and online conversion rates. They typically exploit explicit or implicit user feedback such as ratings, buying records or clickstream data and apply statistical methods to derive recommendations. Collaborative filtering is one of the most widely used approaches in recommender systems. However, the traditional collaborative filtering methods compute users’ similarities in the dimension of products, and they do not take the influence of neighbor users into consideration when computing such similarities. This paper focuses on explicitly formulated user requirements as the sole type of user feedback. The new collaborative filtering method based on user interests’ transmission. This method computes customers’ similarities in the dimension of interests, and takes the interests transmission between different customers into reflection. This method not only can cope with cold start problem and data sparse problem, but also have prediction precision.

Research on System of Data Mining Technology Based on Computer

The existing implicit feedback collaborative algorithm directly uses sparse binary social trust information to assist recommendation, which has serious data sparse problems and does not have the influence of deep integration of social trust information. In response to the above problems, the paper proposes an algorithm that uses a denoising autoencoder to deeply integrate user implicit feedback data and social information. At the same time, a cloud computing-based social trust information data mining system architecture is constructed, and its modules are described. This framework is conducive to solving the problems of high data complexity and large amount of data encountered in current data mining, and can significantly improve the performance of data mining.

Listener Modeling and Context-Aware Music Recommendation Based on Country Archetypes.

Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the “music mainstream” strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervized learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user’s country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-à-vis state-of-the-art algorithms that do not exploit this type of context information.

Neural news recommendation with negative feedback

News recommendation is important for online news services. Precise user interest modeling is critical for personalized news recommendation. Existing news recommendation methods usually rely on the implicit feedback of users like news clicks to model user interest. However, news click may not necessarily reflect user interests because users may click a news due to the attraction of its title but feel disappointed at its content. The dwell time of news reading is an important clue for user interest modeling, since short reading dwell time usually indicates low and even negative interest. Thus, incorporating the negative feedback inferred from the dwell time of news reading can improve the quality of user modeling. In this paper, we propose a neural news recommendation approach which can incorporate the implicit negative user feedback. We propose to distinguish positive and negative news clicks according to their reading dwell time, and respectively learn user representations from positive and negative news clicks via a combination of Transformer and additive attention network. In addition, we propose to compute a positive click score and a negative click score based on the relevance between candidate news representations and the user representations learned from the positive and negative news clicks. The final click score is a combination of positive and negative click scores. Besides, we propose an interactive news modeling method to consider the relatedness between title and body in news modeling. Extensive experiments on real-world dataset validate that our approach can achieve more accurate user interest modeling for news recommendation.

Social recommendation algorithms with user feedback information

SummarySocial media information can effectively improve the performance of personalized recommendation model. However, the feedback information in the social media which can accurately reflect users' implicit preferences is often ignored by most existing methods. To improve the users' experience and reduce the push of unwelcome information, in this article, we propose a new social recommendation algorithm with user feedback information. Different from the existing recommendation methods based on probability matrix decomposition, we incorporate the user implicit feedback information into the user rating prediction function. To reduce the data sparsity of implicit feedback information, we also adopt social network trust calculation in our algorithm. As a result, we can not only optimize the recommendation list but also filter out most of disgusting content. Compared with PMF, UserCF, CUNE, and TrustSVD, but slightly lower than RSTE, the experimental results of our model on real‐world datasets demonstrate the effectiveness of our proposed method, and further verify that the user experience is significantly improved without obviously reducing the accuracy of the recommendation.

Incorporating Multi-Source Urban Data for Personalized and Context-Aware Multi-Modal Transportation Recommendation

Transportation recommendation is one important map service in navigation applications. Previous transportation recommendation solutions fail to deliver satisfactory user experience because their recommendations only consider routes in one transportation mode (uni-modal, e.g., taxi, bus, cycle) and largely overlook situational context. In this work, we propose <inline-formula><tex-math notation="LaTeX">$\mathsf {Hydra}$</tex-math></inline-formula> , a multi-task deep learning based recommendation system that offers multi-modal transportation planning and is adaptive to various situational context (e.g., nearby point-of-interest (POI) distribution and weather). We leverage the availability of existing routing engines and big urban data, and design a novel two-level framework that integrates uni-modal and multi-modal (e.g., taxi-bus, bus-cycle) routes as well as heterogeneous urban data for intelligent multi-modal transportation recommendation. In addition to urban context features constructed from multi-source urban data, we learn the latent representations of users, origin-destination (OD) pairs and transportation modes based on user implicit feedbacks, which captures the collaborative transportation mode preferences of users and OD pairs. Moreover, we propose two models to recommend the proper route among various uni-modal and multi-modal transportation routes: (1) a light-weight gradient boosting decision tree (GBDT) based recommendation model; and (2) a multi-task wide and deep learning (MTWDL) based recommendation model. We also optimize the framework to support real-time, large-scale route query and recommendation. We deploy <inline-formula><tex-math notation="LaTeX">$\mathsf {Hydra}$</tex-math></inline-formula> on Baidu Maps, <xref ref-type="fn" rid="fn1">¹</xref> <fn id="fn1"><label>1.</label> <uri>https://maps.baidu.com/</uri>. </fn> one of the world's largest map services. Real-world urban-scale experiments demonstrate the effectiveness and efficiency of our proposed system. Since its deployment in August 2018, <inline-formula><tex-math notation="LaTeX">$\mathsf {Hydra}$</tex-math></inline-formula> has answered over a hundred million route recommendation queries made by over ten million distinct users. The GBDT based model and MTWDL based model achieve 82.8 and 96.6 percent relative improvement of user click ratio, respectively.

What is of interest for tourists in an alpine destination: personalized recommendations for daily activities based on view data

Smartphones are nowadays important tools for tourists. For instance, while on the go in a destination, tourists can use smartphones to find places of interest and to identify activities that might be of interest, as well as a wealth of related information and even special offers in real-time. However, it is time consuming and not easy for tourists in an unknown destination to choose among the numerous options available. Recommendations for instance from other tourists with similar interests would help immensely. Indeed, places and activities are often reviewed and rated by other tourists, however, this information is typically not personalized. This article proposes a recommender system as part of an evolving mobile destination app. Our recommender app is capable of providing personalized recommendations to tourists thereby facilitating and enriching tourists’ experience and stay. This work is based on two qualitative studies towards exploring the information needs of tourists in an alpine destination. These studies were conducted using the mobile ethnography approach and semi-structured interviews. A hybrid recommender system is proposed that uses implicit user feedback in the form of view duration. The proposed system was tested using real data derived from tourists using the mobile app in a Swiss alpine destination. The results of these experiments demonstrate that the system is capable of providing high-quality and diverse recommendations. The core contribution of this work lies in the transformation of the viewing durations to a set of preference values and in learning the optimized weights of the parameters of a hybrid system utilizing an energy minimization framework.

Personalized recommendation via user preference matching

Graph-based recommendation approaches use a graph model to represent the relationships between users and items, and exploit the graph structure to make recommendations. Recent graph-based recommendation approaches focused on capturing users’ pairwise preferences and utilized a graph model to exploit the relationships between different entities in the graph. In this paper, we focus on the impact of pairwise preferences on the diversity of recommendations. We propose a novel graph-based ranking oriented recommendation algorithm that exploits both explicit and implicit feedback of users. The algorithm utilizes a user-preference-item tripartite graph model and modified resource allocation process to match the target user with users who share similar preferences, and make personalized recommendations. The principle of the additional preference layer is to capture users’ pairwise preferences, provide detailed information of users for further recommendations. Empirical analysis of four benchmark datasets demonstrated that our proposed algorithm performs better in most situations than other graph-based and ranking-oriented benchmark algorithms.

A session‐specific opportunity cost model for rank‐oriented recommendation

Recommender systems are changing the way that people find information, products, and even other people. This paper studies the problem of leveraging the context of the items presented to the user in a user/system interaction session to improve the recommender system's ranking prediction. We propose a novel model that incorporates the opportunity cost of giving up the other items in the session and computes session‐specific relevance values for items for context‐aware recommendation. The model can work on a variety of different problems settings with emphasis on implicit user feedback as it supports varying levels of ordinal relevance. Experimental evaluation demonstrates the advantages of our new model with respect to the ranking quality.

Predicting e-book ranking based on the implicit user feedback

In this paper, we plan to predict a ranking on e-books by analyzing the implicit user behavior, and the goal of our work is to optimize the ranking results to be close to that of the ground truth ranking where e-books are ordered by their corresponding reader number. As far as we know, there exist little work on predicting the future e-book ranking. To this end, through analyzing various user behavior from a popular e-book reading mobile APP, we construct three groups of features that are related to e-book ranking, where some features are created based on the popular metrics from the e-commerce, e.g., conversion rates. Then, we firstly propose a baseline method by using the idea of learning to rank (L2R), where we train the ranking model for each e-book by taking all its past user feedback within a time interval into consideration. Then we further propose TDLR: a Time Decay based Learning to Rank method, where we separately train the ranking model on each day and combine these models by gradually decaying the importance of them over time. Through extensive experimental studies on the real-world dataset, our approach TDLR is proved to significantly improve the e-book ranking quality more than 10% when compared with the L2R method where no time decay is considered.

A user similarity-based Top-N recommendation approach for mobile in-application advertising

Ensuring scalability of recommender systems without sacrificing the quality of the recommendations produced, presents significant challenges, especially in the large-scale, real-world setting of mobile ad targeting. In this paper, we propose MobRec, a novel two-stage user similarity based approach to recommendation which combines information provided by slowly-changing features of the mobile context and implicit user feedback indicative of user preferences. MobRec uses the contextual features to cluster, during an off-line stage, users that share similar patterns of mobile behavior. In the online stage, MobRec focuses on the cluster consisting of users that are most similar to the target user in terms of their contextual features as well as implicit feedback. MobRec also employs a novel strategy for robust estimation of user preferences from noisy clicks. Results of experiments using a large-scale real-world mobile advertising dataset demonstrate that MobRec outperforms the state-of-the-art neighborhood-based as well as latent factor-based recommender systems, in terms of both scalability and the quality of the recommendations.