AMachine Learning Approach to User Profiling for Data Annotation of Online Behavior

The user’s intent to seek online information has been an active area of research in user profiling.User profiling considers user characteristics,behaviors,activities,and preferences to sketch user intentions,interests,and motivations.Determining user characteristics can help capture implicit and explicit preferences and intentions for effective user-centric and customized content presentation.The user’s complete online experience in seeking information is a blend of activities such as searching,verifying,and sharing it on social platforms.However,a combination of multiple behaviors in profiling users has yet to be considered.This research takes a novel approach and explores user intent types based on multidimensional online behavior in information acquisition.This research explores information search,verification,and dissemination behavior and identifies diverse types of users based on their online engagement using machine learning.The research proposes a generic user profile template that explains the user characteristics based on the internet experience and uses it as ground truth for data annotation.User feedback is based on online behavior and practices collected by using a survey method.The participants include both males and females from different occupation sectors and different ages.The data collected is subject to feature engineering,and the significant features are presented to unsupervised machine learning methods to identify user intent classes or profiles and their characteristics.Different techniques are evaluated,and the K-Mean clustering method successfully generates five user groups observing different user characteristics with an average silhouette of 0.36 and a distortion score of 1136.Feature average is computed to identify user intent type characteristics.The user intent classes are then further generalized to create a user intent template with an Inter-Rater Reliability of 75%.This research successfully extracts different user types based on their preferences in online content,platforms,criteria,and frequency.The study also validates the proposed template on user feedback data through Inter-Rater Agreement process using an external human rater.

Joint user profiling with hierarchical attention networks

User profiling by inferring user personality traits,such as age and gender,plays an increasingly important role in many real-world applications.Most existing methods for user profiling either use only one type of data or ignore handling the noisy information of data.Moreover,they usually consider this problem from only one perspective.In this paper,we propose a joint user profiling model with hierarchical attention networks(JUHA)to learn informative user representations for user profiling.Our JUHA method does user profiling based on both inner-user and inter-user features.We explore inner-user features from user behaviors(e.g.,purchased items and posted blogs),and inter-user features from a user-user graph(where similar users could be connected to each other).JUHA learns basic sentence and bag representations from multiple separate sources of data(user behaviors)as the first round of data preparation.In this module,convolutional neural networks(CNNs)are introduced to capture word and sentence features of age and gender while the self-attention mechanism is exploited to weaken the noisy data.Following this,we build another bag which contains a user-user graph.Inter-user features are learned from this bag using propagation information between linked users in the graph.To acquire more robust data,inter-user features and other inner-user bag representations are joined into each sentence in the current bag to learn the final bag representation.Subsequently,all of the bag representations are integrated to lean comprehensive user representation by the self-attention mechanism.Our experimental results demonstrate that our approach outperforms several state-of-the-art methods and improves prediction performance.

Integrating Machine Learning and Evidential Reasoning for User Profiling and Recommendation

User profiles representing users’preferences and interests play an important role in many applications of personalized recommendation.With the rapid growth of social platforms,there is a critical need for efficient solutions to learn user profiles from the information they shared on social platforms so as to improve the quality of recommendation services.The problem of user profile learning is significantly challenging due to difficulty in handling data from multiple sources,in different formats and often associated with uncertainty.In this paper,we introduce an integrated approach that combines advanced Machine Learning techniques with evidential reasoning based on Dempster-Shafer theory of evidence for user profiling and recommendation.The developed methods for user profile learning and multi-criteria collaborative filtering are demonstrated with experimental results and analysis that show the effectiveness and practicality of the integrated approach.A proposal for extending multi-criteria recommendation systems by incorporating user profiles learned from different sources of data into the recommendation process so as to provide better recommendation capabilities is also highlighted.

Feature weighted clustering for user profiling

Personalization is the adaptation of the services to fit the user’s interests,characteristics and needs.The key to effective personalization is user profiling.Apart from traditional collaborative and content-based approaches,a number of classification and clustering algorithms have been used to classify user related information to create user profiles.However,they are not able to achieve accurate user profiles.In this paper,we present a new clustering algorithm,namely Multi-Dimensional Clustering(MDC),to determine user profiling.The MDC is a version of the Instance-Based Learner(IBL)algorithm that assigns weights to feature values and considers these weights for the clustering.Three feature weight methods are proposed for the MDC and,all three,have been tested and evaluated.Simulations were conducted with using two sets of user profile datasets,which are the training(includes 10,000 instances)and test(includes 1000 instances)datasets.These datasets reflect each user’s personal information,preferences and interests.Additional simulations and comparisons with existing weighted and non-weighted instance-based algorithms were carried out in order to demonstrate the performance of proposed algorithm.Experimental results using the user profile datasets demonstrate that the proposed algorithm has better clustering accuracy performance compared to other algorithms.This work is based on the doctoral thesis of the corresponding author.

User Profiling for CSDN:Keyphrase Extraction,User Tagging and User Growth Value Prediction

The Chinese Software Developer Network(CSDN)is one of the largest information technology communities and service platforms in China.This paper describes the user profiling for CSDN,an evaluation track of SMP Cup 2017.It contains three tasks:(1)user document keyphrase extraction,(2)user tagging and(3)user growth value prediction.In the first task,we treat keyphrase extraction as a classification problem and train a Gradient-Boosting-Decision-Tree model with comprehensive features.In the second task,to deal with class imbalance and capture the interdependency between classes,we propose a two-stage framework:(1)for each class,we train a binary classifier to model each class against all of the other classes independently;(2)we feed the output of the trained classifiers into a softmax classifier,tagging each user with multiple labels.In the third task,we propose a comprehensive architecture to predict user growth value.Our contributions in this paper are summarized as follows:(1)we extract various types of features to identify the key factors in user value growth;(2)we use the semi-supervised method and the stacking technique to extend labeled data sets and increase the generality of the trained model,resulting in an impressive performance in our experiments.In the competition,we achieved the first place out of 329 teams.

User Profile in Smart Elderly Care Community:Findings from Community in Western China

With the increase in the aging population,the need for elderly care services has diversified,and smart elderly care has become an effective measure to cope with this increasing aging population.Based on the data from the platform“Guan Hu Tong”of RQ Company in the community of Shaanxi Province in western China,this study mined the data of smart elderly care services through the recency,frequency and monetary value(RFM)model and the backpropagation(BP)neural network model,constructed the user profile of the elderly,and predicted users’practical demands.The following conclusions were drawn:The oldest users are important target users of smart elderly care service platforms;Elderly women living alone rely more on smart elderly care services;Meal delivery and health follow-up services are the most popular among elderly users.

MMLUP: Multi-Source & Multi-Task Learning for User Profiles in Social Network

With the rapid development of the mobile Internet,users generate massive data in different forms in social network every day,and different characteristics of users are reflected by these social media data.How to integrate multiple heterogeneous information and establish user profiles from multiple perspectives plays an important role in providing personalized services,marketing,and recommendation systems.In this paper,we propose Multi-source&Multi-task Learning for User Profiles in Social Network which integrates multiple social data sources and contains a multi-task learning framework to simultaneously predict various attributes of a user.Firstly,we design their own feature extraction models for multiple heterogeneous data sources.Secondly,we design a shared layer to fuse multiple heterogeneous data sources as general shared representation for multi-task learning.Thirdly,we design each task’s own unique presentation layer for discriminant output of specific-task.Finally,we design a weighted loss function to improve the learning efficiency and prediction accuracy of each task.Our experimental results on more than 5000 Sina Weibo users demonstrate that our approach outperforms state-of-the-art baselines for inferring gender,age and region of social media users.

User Profile System Based on Sentiment Analysis for Mobile Edge Computing

Emotions of users do not converge in a single application but are scattered across diverse applications.Mobile devices are the closest media for handling user data and these devices have the advantage of integrating private user information and emotions spread over different applications.In this paper,we first analyze user profile on a mobile device by describing the problem of the user sentiment profile system in terms of data granularity,media diversity,and server-side solution.Fine-grained data requires additional data and structural analysis in mobile devices.Media diversity requires standard parameters to integrate user data from various applications.A server-side solution presents a potential risk when handling individual privacy information.Therefore,in order to overcome these problems,we propose a general-purposed user profile system based on sentiment analysis that extracts individual emotional preferences by comparing the difference between public and individual data based on particular features.The proposed system is built based on a sentiment hierarchy,which is created by using unstructured data on mobile devices.It can compensate for the concentration of single media,and analyze individual private data without the invasion of privacy on mobile devices.

PUMTD:Privacy-Preserving User-Profile Matching Protocol in Social Networks

User profile matching can establish social relationships between different users in the social network.If the user profile is matched in plaintext,the user's privacy might face a security challenge.Although there exist some schemes realizing privacypreserving user profile matching,the resource-limited users or social service providers in these schemes need to take higher computational complexity to ensure the privacy or matching of the data.To overcome the problems,a novel privacy-preserving user profile matching protocol in social networks is proposed by using t-out-of n servers and the bloom filter technique,in which the computational complexity of a user is reduced by applying the Chinese Remainder Theorem,the matching users can be found with the help of any t matching servers,and the privacy of the user profile is not compromised.Furthermore,if at most t-1 servers are allowed to collude,our scheme can still fulfill user profile privacy and user query privacy.Finally,the performance of the proposed scheme is compared with the other two schemes,and the results show that our scheme is superior to them.

Ranking of Web Pages in a Personalized Search

The basic idea behind a personalized web search is to deliver search results that are tailored to meet user needs, which is one of the growing concepts in web technologies. The personalized web search presented in this paper is based on exploiting the implicit feedbacks of user satisfaction during her web browsing history to construct a user profile storing the web pages the user is highly interested in. A weight is assigned to each page stored in the user’s profile;this weight reflects the user’s interest in this page. We name this weight the relative rank of the page, since it depends on the user issuing the query. Therefore, the ranking algorithm provided in this paper is based on the principle that;the rank assigned to a page is the addition of two rank values R_rank and A_rank. A_rank is an absolute rank, since it is fixed for all users issuing the same query, it only depends on the link structures of the web and on the keywords of the query. Thus, it could be calculated by the PageRank algorithm suggested by Brin and Page in 1998 and used by the google search engine. While, R_rank is the relative rank, it is calculated by the methods given in this paper which depends mainly on recording implicit measures of user satisfaction during her previous browsing history.

Masquerade Detection Using Support Vector Machine

A new method using support vector data description (SVDD) to distinguishlegitimate users from mas-queradcrs based on UNIX user command sequences is proposed Sliding windowsare used to get low detection delay. Experiments demonstrate that the detection effect usingenriched sequences is better than that of using truncated sequences. As a SVDD profile is composedof a small amount of support vectors, our SVDD-based method can achieve computation and storageadvantage when the detection performance issimilar to existing method.

ADAPTIVE AND ACTIVE COMPUTING PARADIGM FOR PERSONALIZED INFORMATION SERVICE IN DISTRIBUTED HETERONGEOUS ENVIRONMENT

To solve the problem that traditional pull based information service can’t meet the demand of long term users getting domain information timely and properly, an adaptive and active computing paradigm (AACP) for personalized information service in heterogeneous environment is proposed to provide user centered, push based higsh quality information service timely in a proper way, the motivation of which is generalized as R 4 Service: the right information at the right time in the right way to the right person, upon which formalized algorithms framework of adaptive user profile management, incremental information retrieval, information filtering, and active delivery mechanism are discussed in details. The AACP paradigm serves users in a push based, event driven, interest related, adaptive and active information service mode, which is useful and promising for long term user to gain fresh information instead of polling from kinds of information sources.

基于流式计算的实时用户画像系统研究

大数据环境下,基于海量数据,针对用户画像的精准度和实时性问题,对实时用户画像系统进行了研究工作,提出了一种采用流式计算思想的实时用户画像系统架构。从整体角度梳理分析了用户画像的体系结构,利用消息队列中间件Kafka实时采集不同维度的用户数据,利用大数据分析和机器学习技术构建了相对精准立体的用户画像数据标签体系及用户画像模型,应用Flink框架和数据挖掘技术对多源流式数据进行实时计算处理,深度分析用户,挖掘用户的特征及需求,进而刻画出精准的用户画像,提供精准的个性化信息服务。该架构能准确对用户进行全方位、高精度的画像构建,结果具有较高的实时性和精确度,从而能达到快速且准确地了解用户需求、利用数据服务用户和业务发展的目的。

Discovering User Profiles for Web Personalized Recommendation

With the growing popularity of the World Wide Web, large volume of useraccess data has been gathered automatically by Web servers and stored in Web logs. Discovering andunderstanding user behavior patterns from log files can provide Web personalized recommendationservices. In this paper, a novel clustering method is presented for log files called Clusteringlarge Weblog based on Key Path Model (CWKPM), which is based on user browsing key path model, to getuser behavior profiles. Compared with the previous Boolean model, key path model considers themajor features of users'' accessing to the Web: ordinal, contiguous and duplicate. Moreover, forclustering, it has fewer dimensions. The analysis and experiments show that CWKPM is an efficientand effective approach for clustering large and high-dimension Web logs.

DP-UserPro:differentially private user profile construction and publication

User profiles are widely used in the age of big data.However,generating and releasing user profiles may cause serious privacy leakage,since a large number of personal data are collected and analyzed.In this paper,we propose a differentially private user profile construction method DP-UserPro,which is composed of DP-CLIQUE and privately top-κtags selection.DP-CLIQUE is a differentially private high dimensional data cluster algorithm based on CLIQUE.The multidimensional tag space is divided into cells,Laplace noises are added into the count value of each cell.Based on the breadth-first-search,the largest connected dense cells are clustered into a cluster.Then a privately top-κtags selection approach is proposed based on the score function of each tag,to select the most importantκtags which can represent the characteristics of the cluster.Privacy and utility of DP-UserPro are theoretically analyzed and experimentally evaluated in the last.Comparison experiments are carried out with Tag Suppression algorithm on two real datasets,to measure the False Negative Rate(FNR)and precision.The results show that DP-UserPro outperforms Tag Suppression by 62.5%in the best case and 14.25%in the worst case on FNR,and DP-UserPro is about 21.1%better on precision than that of Tag Suppression,in average.

Identifying User Profile by Incorporating Self-Attention Mechanism based on CSDN Data Set

With the popularity of social media,there has been an increasing interest in user profiling and its applications nowadays.This paper presents our system named UIR-SIST for User Profiling Technology Evaluation Campaign in SMP CUP 2017.UIR-SIST aims to complete three tasks,including keywords extraction from blogs,user interests labeling and user growth value prediction.To this end,we first extract keywords from a user’s blog,including the blog itself,blogs on the same topic and other blogs published by the same user.Then a unified neural network model is constructed based on a convolutional neural network(CNN)for user interests tagging.Finally,we adopt a stacking model for predicting user growth value.We eventually receive the sixth place with evaluation scores of 0.563,0.378 and 0.751 on the three tasks,respectively.

Personalized News Recommendation:A Review and an Experimental Investigation

Online news articles,as a new format of press releases,have sprung up on the Internet.With its convenience and recency,more and more people prefer to read news online instead of reading the paper-format press releases.However,a gigantic amount of news events might be released at a rate of hundreds,even thousands per hour.A challenging problem is how to efficiently select specific news articles from a large corpus of newly-published press releases to recommend to individual readers,where the selected news items should match the reader＇s reading preference as much as possible.This issue refers to personalized news recommendation.Recently,personalized news recommendation has become a promising research direction as the Internet provides fast access to real-time information from multiple sources around the world.Existing personalized news recommendation systems strive to adapt their services to individual users by virtue of both user and news content information.A variety of techniques have been proposed to tackle personalized news recommendation,including content-based,collaborative filtering systems and hybrid versions of these two.In this paper,we provide a comprehensive investigation of existing personalized news recommenders.We discuss several essential issues underlying the problem of personalized news recommendation,and explore possible solutions for performance improvement.Further,we provide an empirical study on a collection of news articles obtained from various news websites,and evaluate the effect of different factors for personalized news recommendation.We hope our discussion and exploration would provide insights for researchers who are interested in personalized news recommendation.

Hybrid Recommender System for Tourism Based on Big Data and AI:A Conceptual Framework

With the development of the Internet,technology,and means of communication,the production of tourist data has multiplied at all levels(hotels,restaurants,transport,heritage,tourist events,activities,etc.),especially with the development of Online Travel Agency(OTA).However,the list of possibilities offered to tourists by these Web search engines(or even specialized tourist sites)can be overwhelming and relevant results are usually drowned in informational"noise",which prevents,or at least slows down the selection process.To assist tourists in trip planning and help them to find the information they are looking for,many recommender systems have been developed.In this article,we present an overview of the various recommendation approaches used in the field of tourism.From this study,an architecture and a conceptual framework for tourism recommender system are proposed,based on a hybrid recommendation approach.The proposed system goes beyond the recommendation of a list of tourist attractions,tailored to tourist preferences.It can be seen as a trip planner that designs a detailed program,including heterogeneous tourism resources,for a specific visit duration.The ultimate goal is to develop a recommender system based on big data technologies,artificial intelligence,and operational research to promote tourism in Morocco,specifically in the Daraa-Tafilalet region.

A semantic web services discovery approach based on a mobile agent using metadata

Purpose-The success of web services involved the adoption of this technology by different service providers through the web,which increased the number of web services,as a result making their discovery a tedious task.The UDDI standard has been proposed for web service publication and discovery.However,it lacks sufficient semantic description in the content of web services,which makes it difficult to find and compose suitable web services during the analysis,search,and matching processes.In addition,few works on semantic web services discovery take into account the user’s profile.The purpose of this paper is to optimize the web services discovery by reducing the search space and increasing the number of relevant services.Design/methodology/approach-The authors propose a new approach for the semantic web services discovery based on the mobile agent,user profile and metadata catalog.In the approach,each user can be described by a profile which is represented in two dimensions:personal dimension and preferences dimension.The description of web service is based on two levels:metadata catalog and WSDL.Findings-First,the semantic web services discovery reduces the number of relevant services through the application of matching algorithm“semantic match”.The result of this first matching restricts the search space at the level of UDDI registry,which allows the users to have good results for the“functional match”.Second,the use of mobile agents as a communication entity reduces the traffic on the network and the quantity of exchanged information.Finally,the integration of user profile in the service discovery process facilitates the expression of the user needs and makes intelligible the selected service.Originality/value-To the best knowledge of the authors,this is the first attempt at implementing the mobile agent technology with the semantic web service technology.