Showing papers on "User modeling published in 2017"

Aspect Based Recommendations: Recommending Items with the Most Valuable Aspects Based on User Reviews

Abstract: In this paper, we propose a recommendation technique that not only can recommend items of interest to the user as traditional recommendation systems do but also specific aspects of consumption of the items to further enhance the user experience with those items. For example, it can recommend the user to go to a specific restaurant (item) and also order some specific foods there, e.g., seafood (an aspect of consumption). Our method is called Sentiment Utility Logistic Model (SULM). As its name suggests, SULM uses sentiment analysis of user reviews. It first predicts the sentiment that the user may have about the item based on what he/she might express about the aspects of the item and then identifies the most valuable aspects of the user's potential experience with that item. Furthermore, the method can recommend items together with those most important aspects over which the user has control and can potentially select them, such as the time to go to a restaurant, e.g. lunch vs. dinner, and what to order there, e.g., seafood. We tested the proposed method on three applications (restaurant, hotel, and beauty & spa) and experimentally showed that those users who followed our recommendations of the most valuable aspects while consuming the items, had better experiences, as defined by the overall rating.

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation

Abstract: A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, which may fail to fully represent the data itself due to limited human instinct. Recent works usually use RNN-based methods to give an overall embedding of a behavior sequence, which then could be exploited by the downstream applications. However, this can only preserve very limited information, or aggregated memories of a person. When a downstream application requires to facilitate the modeled user features, it may lose the integrity of the specific highly correlated behavior of the user, and introduce noises derived from unrelated behaviors. This paper proposes an attention based user behavior modeling framework called ATRank, which we mainly use for recommendation tasks. Heterogeneous user behaviors are considered in our model that we project all types of behaviors into multiple latent semantic spaces, where influence can be made among the behaviors via self-attention. Downstream applications then can use the user behavior vectors via vanilla attention. Experiments show that ATRank can achieve better performance and faster training process. We further explore ATRank to use one unified model to predict different types of user behaviors at the same time, showing a comparable performance with the highly optimized individual models.

Recommending and localizing change requests for mobile apps based on user reviews

Abstract: Researchers have proposed several approaches to extract information from user reviews useful for maintaining and evolving mobile apps. However, most of them just perform automatic classification of user reviews according to specific keywords (e.g., bugs, features). Moreover, they do not provide any support for linking user feedback to the source code components to be changed, thus requiring a manual, time-consuming, and error-prone task. In this paper, we introduce ChangeAdvisor, a novel approach that analyzes the structure, semantics, and sentiments of sentences contained in user reviews to extract useful (user) feedback from maintenance perspectives and recommend to developers changes to software artifacts. It relies on natural language processing and clustering algorithms to group user reviews around similar user needs and suggestions for change. Then, it involves textual based heuristics to determine the code artifacts that need to be maintained according to the recommended software changes. The quantitative and qualitative studies carried out on 44 683 user reviews of 10 open source mobile apps and their original developers showed a high accuracy of ChangeAdvisor in (i) clustering similar user change requests and (ii) identifying the code components impacted by the suggested changes. Moreover, the obtained results show that ChangeAdvisor is more accurate than a baseline approach for linking user feedback clusters to the source code in terms of both precision (+47%) and recall (+38%).

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation.

Abstract: A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, which may fail to fully represent the data itself due to limited human instinct. Recent works usually use RNN-based methods to give an overall embedding of a behavior sequence, which then could be exploited by the downstream applications. However, this can only preserve very limited information, or aggregated memories of a person. When a downstream application requires to facilitate the modeled user features, it may lose the integrity of the specific highly correlated behavior of the user, and introduce noises derived from unrelated behaviors. This paper proposes an attention based user behavior modeling framework called ATRank, which we mainly use for recommendation tasks. Heterogeneous user behaviors are considered in our model that we project all types of behaviors into multiple latent semantic spaces, where influence can be made among the behaviors via self-attention. Downstream applications then can use the user behavior vectors via vanilla attention. Experiments show that ATRank can achieve better performance and faster training process. We further explore ATRank to use one unified model to predict different types of user behaviors at the same time, showing a comparable performance with the highly optimized individual models.

Modeling the Evolution of Users’ Preferences and Social Links in Social Networking Services

Abstract: Sociologists have long converged that the evolution of a S ocial N etworking S ervice(SNS) is driven by the interplay between users’ preferences (reflected in user-item interaction behavior) and the social network structure (reflected in user-user interaction behavior). Nevertheless, traditional approaches either modeled these two kinds of behaviors in isolation or relied on a static assumption of a SNS. Thus, it is still unclear how do the roles of the dynamic social network structure and users’ historical preferences affect the evolution of SNSs. Furthermore, can transforming the underlying social theories in the platform evolution modeling process benefit both behavior prediction tasks? In this paper, we incorporate the underlying social theories to explain and model the evolution of users’ two kinds of behaviors in SNSs. Specifically, we present two kinds of representations for users’ behaviors: a direct (latent) representation that presumes users’ behaviors are represented directly (latently) by their historical behaviors. Under each representation, we associate each user's two kinds of behaviors with two vectors at each time. Then, for each representation, we propose the corresponding learning model to fuse the interplay between users’ two kinds of behaviors. Finally, extensive experimental results demonstrate the effectiveness of our proposed models for both user preference prediction and social link suggestion.

Adaptive KNN based Recommender System through Mining of User Preferences

Abstract: Research for the generation of reliable recommendations has been the main goal focused by many researchers in recent years. Though many recommendation approaches have been developed to assist users in the selection of their interesting items in the online world, still the personalization problem exists. In this paper, we present a new recommendation approach to address the problems such as scalability, sparsity, and cold-start in a collective way. We have developed a knowledge-based domain specific ontology for the generation of personalized recommendations. We have also introduced two different ontology-based predictive models as minion representation model and prominent representation model for the effective generation of recommendations to all types of users. The prediction models are induced by data mining algorithms by correlating the user preferences and features of items for user modeling. We have proposed a new variant of KNN algorithm as Adaptive KNN for the collaborative filtering based recommender system. The proposed recommendation approach is validated with standard MovieLens dataset and obtained results are evaluated with Precision, Recall, F-Measure, and Accuracy. The experimental results had proved the better performance of our proposed AKNN algorithm over other algorithms with the highly sparse data taken for the recommendation generation.

Understanding the Internet of Things ecosystem: multi-level analysis of users, society, and ecology

Abstract: Purpose This study aims to conduct socio-technical analysis of the rapidly evolving Internet of Things (IoT) ecosystem and industry, including such factors as market growth and user experiences, policy and the impact of IoT on various areas. Design/methodology/approach By applying a multi-level socio-technical framework to IoT in South Korea, this study seeks an ecological understanding of how IoT will evolve and stabilize in a smart environment. Findings The study shows the values influencing potential users’ adoption of IoT by integrating cognitive motivations and user values as primary determining factors. Along with user modeling, the findings reveal the challenges of designing, deploying and sustaining the diverse components of IoT, and provides a snapshot of Korea’s current approach to meeting these challenges. Originality/value The study’s findings offer a contextualized socio-technical analysis of IoT, providing insight into its challenges and opportunities. This insight helps to conceptualize how IoT can be designed and situated within human-centered contexts.

User trends modeling for a content-based recommender system

Abstract: Proposing a novel evolutionary model-based recommender system.Introducing the concept of trend to capture dynamics in user interests.Proposing a Bayesian nonparametric model to construct the trend distributions.Adapting the trend-based user model in line with temporal activities of user. Recommender systems have been developed to overcome the information overload problem by retrieving the most relevant resources. Constructing an appropriate model to estimate the user interests is the major task of recommender systems. The profile matching and latent factors are two main approaches for user modeling. Although a notion of timestamps has already been applied to address the temporary nature of recommender systems, the evolutionary behavior of such systems is less studied. In this paper, we introduce the concept of trend to capture the interests of user in selecting items among different group of similar items. The trend based user model is constructed by incorporating user profile into a new extension of Distance Dependent Chines Restaurant Process (dd-CRP). dd-CRP which is a Bayesian Nonparametric model, provides a framework for constructing an evolutionary user model that captures the dynamics of user interests. We evaluate the proposed method using a real-world data-set that contains news tweets of three news agencies (New York Times, BBC and Associated Press). The experimental results and comparisons show the superior recommendation accuracy of the proposed approach, and its ability to effectively evolve over time.

Human Factors, User Requirements, and User Acceptance of Ride-Sharing In Automated Vehicles

Abstract: This paper provides an overview of the social-psychological factors that are likely to influence the trust and acceptance of shared SAE Level 4 Automated Vehicles (AVs). It begins with a short summary of what influences users’ engagement in ride-sharing for conventional vehicles, followed by the factors that affect user acceptance and trust of robotic systems. Using studies of human robot interaction (HRI), recommendations are made on how to improve users’ trust, acceptance and use of shared AVs. Results from real-world studies and on-line surveys provide some contradictory views regarding willingness to accept and use the systems, which may be partly due to the fact that on-line users have not had actual interactions with AVs. We recommend that the pathway to adoption and acceptance of AVs should be incremental and iterative, providing users with hands-on experience of the systems at every stage. This removes unrealistic, idealised, expectations, which can ultimately hamper acceptance. Manufacturers may also use new technologies, social-networks and crowd-sourcing techniques to receive feedback and input from consumers themselves, in order to increase adoption and acceptance of shared AVs.

A Location-Sentiment-Aware Recommender System for Both Home-Town and Out-of-Town Users

Abstract: Spatial item recommendation has become an important means to help people discover interesting locations, especially when people pay a visit to unfamiliar regions. Some current researches are focusing on modelling individual and collective geographical preferences for spatial item recommendation based on users' check-in records, but they fail to explore the phenomenon of user interest drift across geographical regions, i.e., users would show different interests when they travel to different regions. Besides, they ignore the influence of public comments for subsequent users' check-in behaviors. Specifically, it is intuitive that users would refuse to check in to a spatial item whose historical reviews seem negative overall, even though it might fit their interests. Therefore, it is necessary to recommend the right item to the right user at the right location. In this paper, we propose a latent probabilistic generative model called LSARS to mimic the decision-making process of users' check-in activities both in home-town and out-of-town scenarios by adapting to user interest drift and crowd sentiments, which can learn location-aware and sentiment-aware individual interests from the contents of spatial items and user reviews. Due to the sparsity of user activities in out-of-town regions, LSARS is further designed to incorporate the public preferences learned from local users' check-in behaviors. Finally, we deploy LSARS into two practical application scenes: spatial item recommendation and target user discovery. Extensive experiments on two large-scale location-based social networks (LBSNs) datasets show that LSARS achieves better performance than existing state-of-the-art methods.

The Handbook of Multimodal-Multisensor Interfaces, Volume 1: Foundations, User Modeling, and Common Modality Combinations

Abstract: The Handbook of Multimodal-Multisensor Interfaces provides the first authoritative resource on what has become the dominant paradigm for new computer interfaces-user input involving new media (speech, multi-touch, gestures, writing) embedded in multimodal-multisensor interfaces. These interfaces support smartphones, wearables, in-vehicle, robotic, and many other applications that are now highly competitive commercially. This edited collection is written by international experts and pioneers in the field. It provides a textbook for students, and a reference and technology roadmap for professionals working in this rapidly emerging area. Volume 1 of the handbook presents relevant theory and neuroscience foundations for guiding the development of high-performance systems. Additional chapters discuss approaches to user modeling, interface design that supports user choice, synergistic combination of modalities with sensors, and blending of multimodal input and output. They also highlight an in-depth look at the most common multimodal-multisensor combinations- for example, touch and pen input, haptic and non-speech audio output, and speech co-processed with visible lip movements, gaze, gestures, or pen input. A common theme throughout is support for mobility and individual differences among users-including the world's rapidly growing population of seniors. These handbook chapters provide walk-through examples and video illustrations of different system designs and their interactive use. Common terms are defined, and information on practical resources is provided (e.g., software tools, data resources) for hands-on project work to develop and evaluate multimodal-multisensor systems. In the final chapter, experts exchange views on a timely and controversial challenge topic, and how they believe multimodal-multisensor interfaces should be designed in the future to most effectively advance human performance.

Personalized Attraction Recommendation System for Tourists Through Check-In Data

Abstract: Online social networks now play a prominent role in our daily lives and our decisions and behaviors in many areas. Of particular interest here is the application of social network data to give users access to tourist information. There is a growing need for information on tourism and tourist activities to satisfy user queries in this domain. Social networks, such as Facebook, Twitter, and Foursquare, among others, store substantial volumes of check-in data, which are a valuable resource for recommending tourism attractions. However, using Facebook check-in data has rarely been considered in conventional recommendation systems (RSs). This presents not only a new research challenge for the computer science and information technology fields but also an interesting opportunity for the tourism industry: knowing what kind of attractions tourists are interested in and how to acquire their user preferences without adding tasks to users of an RS. We propose a tourism RS that is based on its recommendations on data dynamically aggregated and extrapolated from the Facebook check-in data. In addition, the so-called “cold-start” problem has been resolved by using users’ Friends’ check-in data to analyze ongoing Facebook activity and update user profiles in the system. Most Facebook users have a well-extended list of Friends. Consequently, the proposed system can dynamically learn user behavior and appropriately adapt recommendations. This paper demonstrate the usefulness of the data available on Facebook through the example studies involving attraction recommendations, resolving the cold-start problem, and adapting the user model to improve recommendation quality in the tourism domain.

Rule-based tools for the configuration of ambient intelligence systems: a comparative user study

Abstract: This paper describes a 63-participant user study that compares two widely known systems supporting end users in creating trigger-action rules for the Internet of Things and Ambient Intelligence scenarios. The user study is the first stage of a research agenda that concerns the implementation of a novel conceptual framework for the design and continuous evolution of `sentient multimedia systems', namely socio-technical systems, where people and many kinds of hardware/software components (sensors, robots, smart devices, web services, etc.) interact with one another through the exchange of multimedia information, to give rise to intelligent, proactive behaviors. The conceptual framework is structured along three layers - physical, inference and user --- and is based on an information space of events, conditions and actions, linked together in Event-Condition-Action rules and operating according to the interconnection metaphor. The results of the user study have provided some indications for the implementation of the user layer, suggesting which could be the most suitable interaction style for rule design by a community of end users (e.g. a family) and which issues should be addressed in such a wide context.

A Grammar-based Approach for Modeling User Interactions and Generating Suggestions During the Data Exploration Process

Abstract: Despite the recent popularity of visual analytics focusing on big data, little is known about how to support users that use visualization techniques to explore multi-dimensional datasets and accomplish specific tasks. Our lack of models that can assist end-users during the data exploration process has made it challenging to learn from the user's interactive and analytical process. The ability to model how a user interacts with a specific visualization technique and what difficulties they face are paramount in supporting individuals with discovering new patterns within their complex datasets. This paper introduces the notion of visualization systems understanding and modeling user interactions with the intent of guiding a user through a task thereby enhancing visual data exploration. The challenges faced and the necessary future steps to take are discussed; and to provide a working example, a grammar-based model is presented that can learn from user interactions, determine the common patterns among a number of subjects using a K-Reversible algorithm, build a set of rules, and apply those rules in the form of suggestions to new users with the goal of guiding them along their visual analytic process. A formal evaluation study with 300 subjects was performed showing that our grammar-based model is effective at capturing the interactive process followed by users and that further research in this area has the potential to positively impact how users interact with a visualization system.

A content-based movie recommender system based on temporal user preferences

Abstract: Recommender systems have emerged as the essential part of many e-commerce web sites. These systems provide personalized services to assist users in finding favorite items among the huge number of available media on the World Wide Web. Identifying temporal preferences of individuals is one of the major challenges of recommender systems to provide personalization for users. In this paper, a content-based movie recommender system is proposed that captures the temporal user preferences in user modeling and predicts the preferred movies. The proposed method provides a user-centered framework that incorporates the content attributes of rated movies (for each user) into a Dirichlet Process Mixture Model to infer user preferences and provide a proper recommendation list. We implement the proposed method and use the MovieLens dataset to perform experiments. The evaluation results show that the performance of proposed recommendation method outperforms the existing movie recommender systems.

Predicting Age and Gender by Keystroke Dynamics and Mouse Patterns

Abstract: In human computer interaction, some of the user activities are intentional, and other unintentional, but user interfaces are usually designed to react only to intentional commands. However, user's unintentional activity contains many clues about a user, that can be beneficial to take into account in designing appropriate response. Current study focuses on these unintentional traces, that left behind by use of standard input devices, keyboard and mouse, and specifically, we try to predict users age and gender. Mouse and keyboard data used in this study, are collected in six different systems between 2011 and 2017 in total from 1519 subjects. Some supervised machine learning models yield to f-scores over 0.9 when predicted both user age or gender.

TF-IDuF : A Novel Term-Weighting Scheme for User Modeling based on Users’ Personal Document Collections

Abstract: TF-IDF is one of the most popular term-weighting schemes, and is applied by search engines, recommender systems, and user modeling engines. With regard to user modeling and recommender systems, we see two shortcomings of TF-IDF. First, calculating IDF requires access to the document corpus from which recommendations are made. Such access is not always given in a user-modeling or recommender system. Second, TF-IDF ignores information from a user’s personal document collection, which could – so we hypothesize – enhance the user modeling process. In this paper, we introduce TFIDuF as a term-weighting scheme that does not require access to the general document corpus and that considers information from the users’ personal document collections. We evaluated the effectiveness of TF-IDuF compared to TF-IDF and TF-Only and found that TF-IDF and TF-IDuF perform similarly (clickthrough rates (CTR) of 5.09% vs. 5.14%), and both are around 25% more effective than TF-Only (CTR of 4.06%) for recommending research papers. Consequently, we conclude that TF-IDuF could be a promising term-weighting scheme, especially when access to the document corpus for recommendations is not possible, and thus classic IDF cannot be computed. It is also notable that TF-IDuF and TF-IDF are not exclusive, so that both metrics may be combined to a more effective term-weighting scheme.

Evaluating Web Search with a Bejeweled Player Model

Abstract: The design of a Web search evaluation metric is closely related with how the user's interaction process is modeled. Each behavioral model results in a different metric used to evaluate search performance. In these models and the user behavior assumptions behind them, when a user ends a search session is one of the prime concerns because it is highly related to both benefit and cost estimation. Existing metric design usually adopts some simplified criteria to decide the stopping time point: (1) upper limit for benefit (e.g. RR, AP); (2) upper limit for cost (e.g. Precision@N, DCG@N). However, in many practical search sessions (e.g. exploratory search), the stopping criterion is more complex than the simplified case. Analyzing benefit and cost of actual users' search sessions, we find that the stopping criteria vary with search tasks and are usually combination effects of both benefit and cost factors. Inspired by a popular computer game named Bejeweled, we propose a Bejeweled Player Model (BPM) to simulate users' search interaction processes and evaluate their search performances. In the BPM, a user stops when he/she either has found sufficient useful information or has no more patience to continue. Given this assumption, a new evaluation framework based on upper limits (either fixed or changeable as search proceeds) for both benefit and cost is proposed. We show how to derive a new metric from the framework and demonstrate that it can be adopted to revise traditional metrics like Discounted Cumulative Gain (DCG), Expected Reciprocal Rank (ERR) and Average Precision (AP). To show effectiveness of the proposed framework, we compare it with a number of existing metrics in terms of correlation between user satisfaction and the metrics based on a dataset that collects users' explicit satisfaction feedbacks and assessors' relevance judgements. Experiment results show that the framework is better correlated with user satisfaction feedbacks.

Fingerprint based smart phone user verification

Abstract: A touchscreen, now incorporated in most smartphones, tablets, laptops, and similar devices, presents an effective and transparent method to incorporate continuous active user verification schemes. The touchscreen element grid structure can be used to capture information, such as a set of one-dimensional time-varying signals produced as the user's finger moves past the grid intersections points. This information may be used to verify the user, or that a valid user currently has possession of the mobile device, even while the user is not consciously engaged in an active verification process. Further functions, such as habitual gesture recognition, can also be performed using the same grid outputs.

Multi-site User Behavior Modeling and Its Application in Video Recommendation

Abstract: As online video service continues to grow in popularity, video content providers compete hard for more eyeball engagement. Some users visit multiple video sites to enjoy videos of their interest while some visit exclusively one site. However, due to the isolation of data, mining and exploiting user behaviors in multiple video websites remain unexplored so far. In this work, we try to model user preferences in six popular video websites with user viewing records obtained from a large ISP in China. The empirical study shows that users exhibit both consistent cross-site interests as well as site-specific interests. To represent this dichotomous pattern of user preferences, we propose a generative model of Multi-site Probabilistic Factorization (MPF) to capture both the cross-site as well as site-specific preferences. Besides, we discuss the design principle of our model by analyzing the sources of the observed site-specific user preferences, namely, site peculiarity and data sparsity. Through conducting extensive recommendation validation, we show that our MPF model achieves the best results compared to several other state-of-the-art factorization models with significant improvements of F-measure by 12.96%, 8.24% and 6.88%, respectively. Our findings provide insights on the value of integrating user data from multiple sites, which stimulates collaboration between video service providers.

Adaptive user modelling in car racing games using behavioural and physiological data

Abstract: Personalised content adaptation has great potential to increase user engagement in video games. Procedural generation of user-tailored content increases the self-motivation of players as they immerse themselves in the virtual world. An adaptive user model is needed to capture the skills of the player and enable automatic game content altering algorithms to fit the individual user. We propose an adaptive user modelling approach using a combination of unobtrusive physiological data to identify strengths and weaknesses in user performance in car racing games. Our system creates user-tailored tracks to improve driving habits and user experience, and to keep engagement at high levels. The user modelling approach adopts concepts from the Trace Theory framework; it uses machine learning to extract features from the user's physiological data and game-related actions, and cluster them into low level primitives. These primitives are transformed and evaluated into higher level abstractions such as experience, exploration and attention. These abstractions are subsequently used to provide track alteration decisions for the player. Collection of data and feedback from 52 users allowed us to associate key model variables and outcomes to user responses, and to verify that the model provides statistically significant decisions personalised to the individual player. Tailored game content variations between users in our experiments, as well as the correlations with user satisfaction demonstrate that our algorithm is able to automatically incorporate user feedback in subsequent procedural content generation.

Artificial intelligence-based object pushing method and apparatus

Abstract: The invention provides an artificial intelligence-based object pushing method and apparatus. The method comprises the steps of inputting historical click behaviors of a target user to a built user model for performing learning to obtain multi-dimensional preference eigenvectors of a target user; obtaining eigenvectors of all to-be-pushed objects; inputting the eigenvectors of the to-be-pushed objects and the multi-dimensional preference eigenvectors to a trained deep neural network model for performing prediction to obtain prediction probabilities of the to-be-pushed objects; and pushing the to-be-pushed objects to the target user according to the obtained prediction probabilities. According to the method and the apparatus, the preferences of the target user are obtained through the user model built by a neural network, and the probability of possibly purchasing to-be-pushed group orders by the target user is obtained based on the deep neural network and the preferences of the target user, so that the pushing is more effective; and preference features are selected through training by the user model, so that a large amount of manpower does not need to be consumed for selection and the pushing efficiency is improved.

The Recommendation System of Micro-Blog Topic Based on User Clustering

Abstract: As a type of crowdsensing media, micro-blog has become an important crowdsensing place for a lot of real-time information dissemination and discussion. With the increasing of micro-blog users, there are more and more new topics emerging on this kind of platform, which has made the users difficult in finding out their own interesting topics. To solve this problem, this paper proposes a micro-blog topic recommendation system which can give corresponding suggestions/strategies for users. Firstly, the user relationship (i.e., a user adds a follow hyperlink to another user) in micro-blog can be effectively analyzed and saved to the user graph. In addition, an algorithm of computing user authority (which is similar to the idea of PageRank) is proposed to catch influential users based on the built user graph. Secondly, Topic Feature Graph (TFG) and User Micro-blog Feature Graph (UMFG) are respectively constructed based on the micro-blog text corpus of a topic and the micro-blog texts followed by a given user. Based on TFG and UMFG, User Topic Feature Vector (UTFV) and User Topic Feature Matrix (UTFM) can be achieved. After that, users' similarity is calculated based on the User Topic Feature Vector and User Topic Feature Matrix to realize the users clustering by the help of the hierarchical clustering algorithm. Incorporating topic heat degree and user authority, the recommendation algorithm is presented to realize Micro-blog topic personalized recommendation within user clustering set. Experiments show that our proposed recommendation system has a good accuracy which is up to 50.2%.