Generate User Profiles Research Articles

System for Selecting Tourist Routes Based on Genetic Programming

One of the most important tasks in tourism is helping tourists plan a trip to a given place. Since it is impossible to visit all places, tourists try to be rational and choose what they find most acceptable and attractive. Each plan has limitations (e. g., length of tour, limited budget) and preferences (e. g., art, culture, historical sites, architecture, modernism) that should be considered when planning your travel trip. This is a special case of the Orientation problem — Tourist trip design problem. The goal is to maximize the total score achieved within a given tour duration limit. This paper focuses on developing a recommendation system that considers users limitations during tour planning and their preferences. Since this problem is an NP-hard problem, heuristic algorithms such as the genetic algorithm (GA) are well suited for solving it. However, this algorithm can take a very long time to find the optimal solution, so this article focuses on developing a greedy strategy of GA to find optimal or near-optimal solutions. Instead of random genetic transformations, the algorithm consciously modifies optimal routes in order to find the desired tour for the users in a shorter time. After this, the developed algorithm was compared with a GA using various generated user profiles. Over 700 locations in Novosibirsk were used as a dataset for making recommendations. These modifications made it possible to obtain optimal routes faster than the standard implementation of the genetic algorithm.

Data mining analytics investigation on TikTok users' behaviors: social media app development

PurposeTikTok, a social media application (app), was originally positioned as a short music video community suitable for young users, and the app is user-generated content (UGC) short video of vertical music. Users can make their own creative videos. Following the rhythm of the music, users can shoot various video content, personal talents, life records, performances, dances, plot interpretations, etc. However, what are the profiles and preferences of TikTok users, whereby the social media app is mainly developed by UGC? What is the impact of TikTok on the development of social media? In addition, what is UGC's social media model for user interactions in social networks? The purpose of this paper is to address and study these proposed issues.Design/methodology/approachAll questionnaire items are designed as nominal and ordinal scales (not Likert scale). The obtained data from questionnaires are put into the relational database (N = 2,011). This empirical study takes Taiwan TikTok users as the research object, implements data mining analytics to generate user profiles through clustering analysis and further uses association rules’ analysis to analyze social media apps in social network interaction and social apps’ development by proposing two patterns and several meaningful rules.FindingsThis study finds that social media apps is a valuable practical research topic on online social media development. In addition, besides the TikTok, the authors eagerly await subsequent research to provide more valuable findings of social media apps in both theory and practice.Originality/valueThis study presents the research evidences that social media apps such as TikTok will be able to transcend the current development pattern of social media and make good use of the media and technology innovation of apps in social development and social informatics.

Latent vehicle type propensity segments: Considering the influence of household vehicle fleet structure

This study applies latent class cluster analysis to a sample of 1,111 survey respondents in Georgia, identifying naturally occurring vehicle type segments based on the influence of both individual vehicle type choices and household vehicle fleet structures. The developed model identifies seven latent vehicle type propensity segments, six of which include individuals who reported being the main driver for (respectively) car, SUV/van, and truck. In three of those segments this was generally their only available vehicle, while in the other three the “main driver” vehicle accompanied other available household vehicles. The seventh segment captures individuals who are main drivers of multiple vehicle types, and who also have other household vehicles available for use. We generate user profiles and discuss differences across segments regarding individual-level characteristics (e.g., gender), household-level characteristics (e.g., household income), land-use and travel-related preferences (e.g., neighborhood type, share of household-serving trips), attitudes (e.g., materialistic), and targeted marketing data variables (e.g., support for charitable causes). Selected results suggest that women choose SUVs/vans due to both personal preferences (e.g., feeling safer while driving a large vehicle) and household responsibilities; show that vehicle-owning behaviors and attitudes are generally consistent, except that strong pro-vehicle-owning attitudes exist within vehicle-deficit households; and suggest that vehicle-deficit households may be less open to alternative fuel vehicles, possibly due to reliability concerns. Overall, this study provides a new perspective on vehicle type propensity segments, and examines the association of a novel range of general and travel-related attributes with these segments, yielding nuanced insights with potential policy implications.

‘IT’S MY FAULT FOR POSTING IN THE FIRST PLACE’: HOW INDIVIDUAL RESPONSIBILITY AND SELF-BLAME ARE SUSTAINED AND INTERNALIZED

Data breaches and data misuse are frequent occurrences in today’s digital society and often spark debate over who should hold responsibility. While many hold the platforms responsible when confronted with violations of data privacy, some users shift the blame inward for trusting the platforms and posting on them. While a large body of research has dedicated itself to issues of data privacy, discourses of individual responsibility and the internalization of user self-blame have received less attention. This study explores how users respond to unknown use of their personal data through the case of CrystalKnows, a personality detection algorithm that generated profiles about individuals using unknown data sources, often without the user’s knowledge. Founded in 2015, CrystalKnows claims to have the world’s largest personality database, providing and selling algorithmically generated user profiles, often without the express consent of these individuals. Interviews were conducted with individuals whose profiles appeared on the platform (N=37) to reveal users’ reactions and rationalizations of the data collected about them. Rationales of self-blame vary but commonly center issues of ambiguity concerning digital consent and the algorithm itself. Ultimately, these contribute to feelings of resignation often paired with the unrealistic alternative of total platform non-use. We argue that these complex discourses of self-blame, independence/choice, and resignation/non-use as the only options are intertwined with data privacy reform efforts. Understanding the sources of self-blame and how deep it runs is an important step to interrogating and refuting some of these assumptions, if broader reforms hope to garner support and implementation.

A Framework for User Adaptation and Profiling for Social Robotics in Rehabilitation.

Physical rehabilitation therapies for children present a challenge, and its success—the improvement of the patient’s condition—depends on many factors, such as the patient’s attitude and motivation, the correct execution of the exercises prescribed by the specialist or his progressive recovery during the therapy. With the aim to increase the benefits of these therapies, social humanoid robots with a friendly aspect represent a promising tool not only to boost the interaction with the pediatric patient, but also to assist physicians in their work. To achieve both goals, it is essential to monitor in detail the patient’s condition, trying to generate user profile models which enhance the feedback with both the system and the specialist. This paper describes how the project NAOTherapist—a robotic architecture for rehabilitation with social robots—has been upgraded in order to include a monitoring system able to generate user profile models through the interaction with the patient, performing user-adapted therapies. Furthermore, the system has been improved by integrating a machine learning algorithm which recognizes the pose adopted by the patient and by adding a clinical reports generation system based on the QUEST metric.

Winners or Victims? Discussing Identity Tracking and Behavior Analysis in Next-Gen Video Games from a Digital Civil Rights Perspective

The purpose of this article is to apply societal discourses on ‘big data’ to the growing practice of the collection of individual information and behavioral patterns of video game players to create virtual player representations. Game developers make use of such data to enhance the gameplay experience, and publishers can learn more about their customers. This article explains technical backgrounds and reasons why developers and publishers have an interest in gathering such a vast load of data. It also explains server gaming and game metrics technologies, takes a look at methods of consumer research, and discusses a critical standpoint from a civil rights perspective. While single aspects of the topic like big data or data mining have been researched and discussed before, the fact that many of today´s video games are constantly retrieving, collecting and maintaining personal data about the players to learn about their patterns of behavior had much less coverage thus far. From a civil rights perspective new dangers arise beyond the widely discussed topics of virtual violence or obsessive gaming and gambling. As a result, it highlights the necessity that modern computer game players should view themselves as vital parts of information networks and, in return for being entertained, provide important personal information that can help to make their individual behavior transparent and usable for third parties and probably information brokers. Not only do providers of games benefit from the socioeconomic information users give, but security agencies and human resource consultants also share a vital interest in any behavioural data that makes an individual become transparent and predictable. Intelligence services, corporations and social networks generate user profiles from data previously submitted during gameplay. This could have a significant impact on future job and life prospects and aid the economic and political control of individuals since character traits like cowardize or courage and sociality become traceable.

Social Networking, Management Responsibilities, and Employee Rights: The Evolving Role of Social Networking in Employment Decisions

In the past decade, social networking sites (SNSs) have transformed the way people socialize. They allow individuals to connect globally and instantaneously. These connections, however, generate user profiles that provide an abundance of personal and behavioral information that can be used as a management tool in the selection process and as a way to monitor potentially detrimental employee activities. Employers can, with relative ease and low cost, access information that would not have been otherwise available. Because employees use and view SNSs in markedly different ways than employers view and use them, these conflicting perspectives and different interests pose serious issues as SNSs continue to grow. Regulations typically lag technology, and research regarding SNSs is limited. Thus, while there is clear potential for using SNSs as human resource tools, there are few legal guidelines controlling their use, little knowledge of their effectiveness, considerable disagreement over privacy and ethical issues, and some potential for abuse. Consequently, proponents and opponents continue to debate the legal, ethical, and practical issues of using SNSs in both staffing and employee monitoring processes. This paper examines these issues and provides guidelines on how managers should use SNSs in managerial decision making.

Pattern-based causal relationships discovery from event sequences for modeling behavioral user profile in ubiquitous environments

This paper presents a novel and practical model for behavioral user profile modeling using causal relationships. In this model, causal relationships, which represent the influence among variables, are discovered from event sequences representing users behaviors, and used for modeling behavioral user profiles. Our model first discovers significant patterns using probabilistic suffix trees, and then discovers pattern correlations using a new sequence clustering algorithm and a modified version of the normalized mutual information (NMI) measure. Causal relationships between the significant patterns are then discovered using the transfer entropy approach. These relationships are used to construct the causal graphs of activities to generate user profiles. Through extensive experiments over a variety of datasets, we empirically demonstrate that these causality-based profiles lead to significant improvement of performance in activity prediction and user identification. We also show that our proposed model is generic and effective in constructing individual user profiles and common profiles for groups of users, in indoor and outdoor environments.

Personalizing news content: An experimental study

The delivery of personalized news content depends on the ability to predict user interests. We evaluated different methods for acquiring user profiles based on declared and actual interest in various news topics and items. In an experiment, 36 students rated their interest in six news topics and in specific news items and read on 6 days standard, nonpersonalized editions and personalized (basic or adaptive) news editions. We measured subjective satisfaction with the editions and expressed preferences, along with objective measures, to infer actual interest in items. Users' declared interest in news topics did not strongly predict their actual interest in specific news items. Satisfaction with all news editions was high, but participants preferred the personalized editions. User interest was weakly correlated with reading duration, article length, and reading order. Different measures predicted interest in different news topics. Explicit measures predicted interest in relatively clearly defined topics such as sports, but were less appropriate for broader topics such as science and technology. Our results indicate that explicit and implicit methods should be combined to generate user profiles. We suggest that a personalized newspaper should contain both general information and personalized items, selected based on specific combinations of measures for each of the different news topics. Based on the findings, we present a general model to decide on the personalization of news content to generate personalized editions for readers.

Incorporating Hidden Markov Model into Anomaly Detection Technique for Network Intrusion Detection

Now-a-days to increase the computation efficiency distributed systems are used in which the computing resources are shared among several systems. Such openness of distributed system leads to increase in potential attacks on the hardware and software by exploration of system vulnerability. This paper presents implementation of Intrusion Detection System (IDS) to model the behavior of users using Hidden Markov Model (HMM). This model attempts to detect intrusive attack efficiently. The IDS is an identification system which can be characterized by probabilities of false acceptance and false rejection. False acceptance means that the IDS allow intruders to continue their activity. False rejection means that the IDS stops the activity of a legitimate user. IDS can be developed by adoption of an appropriate mathematical model that allows us to generate user profiles efficiently and facilitates an effective and accurate decision-making process for intrusion detection. Due to the nondeterministic nature of user behavior, the decision about intrusive or nonintrusive behavior must take into account all evidence for and against the claim. So the probabilistic approach is to be implemented to model user profile to detect attack.

Semantic Tag-based Profile Framework for Social Tagging Systems

Social tags have recently become popular for use as keywords for searching and annotating Web resources. The main limitation of using social tags is the focus on the keyword and human interpretability rather than on semantics and computer interpretability. Hence, although social tags are useful for information sharing and organizing, they lack the semantic metadata needed for the reasoning and inference functions that facilitate a personalized Web resource search. This study addresses this issue by defining a Semantic Tag-based Profile Framework (STPF) for integrating ontology technologies into user profiles and Web resource annotations. The proposed STPF is applied in a novel algorithm for automatically generating user profiles by combining the traditional term frequency scheme and the semantic technology. A Semantic Tag-based User Profile Platform (STUPP) based on the proposed STPF and algorithm is also used as a broker for personalized Web resource searches made for individual needs. The experimental results show that the proposed approach has higher precision and recall than the traditional term frequency scheme.

Effective Personalized Web Mining by Utilizing the Most Utilized Data

Looking into the growth of information in the web it is a very tedious process of getting the exact information the user is looking for. Many search engines generate user profile related data listing. This paper involves one such process where the rating is given to the link that the user is clicking on. Rather than avoiding the uninterested links both interested links and the uninterested links are listed. But sorted according to the weightings given to each link by the number of visit made by the particular user and the amount of time spent on the particular link.

A Comparison of Generated Wikipedia Profiles Using Social Labeling and Automatic Keyword Extraction

In many collaborative systems, researchers are interested in creating representative user profiles. In this paper, we are particularly interested in using social labeling and automatic keyword extraction techniques for generating user profiles. Social labeling is a process in which users manually tag other users with keywords. Automatic keyword extraction is a technique that selects the most salient words to represent a user’s contribution. We apply each of these two profile generation methods to highly active Wikipedia editors and their contributions, and compare the results. We found that profiles generated through social labeling matches the profiles generated via automatic keyword extraction, and vice versa. The results suggest that user profiles generated from one method can be used as a seed or bootstrapping proxy for the other method.

Profile Generation for TV Program Recommendation Based on Utterance Analysis

This paper proposes a method for generating user profile that is to be used for TV program recommendation. The proposed method does not estimate user's interest in a TV program only based on its watching time as most of existing methods do, but also based on user's utterances by applying sentiment analysis. Three kinds of scores are calculated for each watched program, based on which fuzzy inference is performed to estimate its rating. After the estimation, profile structure is obtained by generating category and subcategory layers. This paper mainly focuses on estimation of users' ratings on TV programs. Experiments are performed with test subjects, and the results show the proposed method can improve the estimation accuracy of ratings compared with existing approach using only watching time. Although the proposed method includes language-dependent processing, it is expected the core of estimation rating can be applied to other languages.

Adaptive eye-gaze tracking using neural-network-based user profiles to assist people with motor disability

This study developed an adaptive real-time human-computer interface (HCI) that serves as an assistive technology tool for people with severe motor disability. The proposed HCI design uses eye gaze as the primary computer input device. Controlling the mouse cursor with raw eye coordinates results in sporadic motion of the pointer because of the saccadic nature of the eye. Even though eye movements are subtle and completely imperceptible under normal circumstances, they considerably affect the accuracy of an eye-gaze-based HCI. The proposed HCI system is novel because it adapts to each specific user's different and potentially changing jitter characteristics through the configuration and training of an artificial neural network (ANN) that is structured to minimize the mouse jitter. This task is based on feeding the ANN a user's initially recorded eye-gaze behavior through a short training session. The ANN finds the relationship between the gaze coordinates and the mouse cursor position based on the multilayer perceptron model. An embedded graphical interface is used during the training session to generate user profiles that make up these unique ANN configurations. The results with 12 subjects in test 1, which involved following a moving target, showed an average jitter reduction of 35%; the results with 9 subjects in test 2, which involved following the contour of a square object, showed an average jitter reduction of 53%. For both results, the outcomes led to trajectories that were significantly smoother and apt at reaching fixed or moving targets with relative ease and within a 5% error margin or deviation from desired trajectories. The positive effects of such jitter reduction are presented graphically for visual appreciation.

Analysis of annotations on documents for recycling of information

AbstractIn order to make collaborative business activities fruitful, it is essential to know characteristics of organizations and persons in more details and to gather information relevant to the activities. In this paper, we describe a notion of “information recycling” that actualizes these requirements by analyzing documents. The key of recycling information is to utilize annotations on documents as clues for generating user profiles and for weighting contents in the context of the activities. We also propose a method of extracting annotations on paper documents just by pressing one button with the help of techniques of camera‐based document image analysis. Experimental results demonstrate that it is fundamentally capable of acquiring annotations on paper documents on the condition that their electronic versions without annotations are available for the processing. © 2008 Wiley Periodicals, Inc. Electr Eng Jpn, 165(2): 60–68, 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20516

Mining Association Rules from TV Watching Log for TV Program Recommendation

This paper proposes a method for extracting association rules from users’ TV watching logs, aiming at TV program recommendation. In Japan, a TV is usually located in a living room, where family members communicate each other while watching the same TV programs. Based on the choice of TV channels and conversation while watching TV, we can estimate other person’s interests and preference, which is a basis for establishing friendly relationship between others. Therefore, giving the robot a capability of recommending TV program will contribute to establish friendly communication with human partners. Furthermore, transition to digital terrestrial television broadcasting (DTTB) will bring us difficulty in finding TV program worth watching from a number of TV channels in near future. Therefore, a method for recommending TV programs will be one of the most important technologies for realizing intelligent support of our daily lives, such as a partner robot. The proposed method extracts association rules from user profiles that are generated from their TV watching logs, based on which TV programs are recommend to a target user. In order to have extensibility in terms of information resource for generating user profile, the method employs a user profile of commonly-used bookmark format. When association rules are extracted from a set of the profiles, generalization law is introduced so that variety of users’ behaviors can be reduced. Experiments are performed with actual users’ logs, and the result shows the generalization law contributes to increase the accuracy of TV program recommendation.

Concept lattices for visualizing and generating user profiles for context-aware service recommendations

Estimating user profiles for service recommendations in an efficient and manageable manner is very important. In a mobile setting, the service recommendation is more likely to depend on context. Since context data are multi-leveled, easy to reconfigure and dynamically changing, a sophisticated mechanism to handle these characteristics when mining for useful rules for ad hoc service recommendations from contextual data is necessary. Moreover, estimating the dynamic changes of the user profiles according to the change of context under a mobile setting is critical for context-aware service recommendations. However, legacy recommender systems having this capability are still quite rare. Hence, this paper aims to propose a user profile-discovering methodology. To do so, a concept lattice, which we will call the profile lattice, is considered for visualizing and generating user profile rules.

RFID-based user profiling of fashion preferences: blueprint for a smart wardrobe

In this paper, we explore the possibility of generating user profiles of fashion preferences from information captured by RFID technology. Proposing a design of a smart wardrobe, we investigate the appropriateness of the technology as an identification tool of real objects and to aid in detecting and tracking real objects movements. We then present a model of user fashion profile, which is generated through queries and data mining techniques. In order to illustrate the usefulness and real world feasibility of our proposed model, we build a working prototype as proof of concept. For evaluation purposes, we have created a random generator, which is able to generate random clothing items and dressing events that serve as input to our model for creating user profiles. Our experimental results clearly indicate that RFID technology is suitable to aid in creating smart systems.

시멘틱 웹 환경에서의 개인화 검색

웹에 분산된 모든 윈 페이지는 구조가 서로 다르다. 시멘틱 웹 환경은 이형적인 구조를 갖는 웹 페이지들의 메타데이터 바탕으로 시멘틱 검색이 가능하다. 그러나 일반적으로 사용자의 요구에 따른 시멘틱 김색은 상황에 따라 엄청난 수의 검색 결과를 내놓는다. 따라서 검색 결과에 대해 각 사용자에 맞는 검색 결과 순위를 적용할 필요가 있다. Culture Finder는 시멘틱 웹 검색 에이전트들이 개인화 된 문화 정보를 검색할 수 있도록 도움을 준다. Culture Finder는 웹에 존재하는 각 웹 페이지에 대한 메타 데이터를 작성하고, 시멘틱 검색을 이행하며 사용자 프로파일을 기반으로 삼아 검색 결과에 대한 순위 점수를 계산한다. Culture Finder에는 개인화 된 시멘틱 검색을 효율적으로 실행하기 위해 중요한 5가지 기법이 적용되었다. 사용자의 검색 행위로부터 사용자 프로파일을 생성하기 위한 기계 학습기법, 시멘틱 웹 검색 에이전트를 위한 효율적인 시멘틱 검색 기법, 사용자 질의의 효과적인 파악을 위한 질의 분석 기법, 각 사용자에게 적합한 검색 결과를 제공하기 위한 순위 적용 기술, 메타데이터를 생성하기 위한 상위 온톨로지 표현 방법, 본 논문에서는 Culture Finder의 구조를 통해서 시멘틱 개인화 검색에 대한 기법을 제안한다. The semantic web environment promise semantic search of heterogeneous data from distributed web page. Semantic search would resuit in an overwhelming number of results for users is increased, therefore elevating the need for appropriate personalized ranking schemes. Culture Finder helps semantic web agents obtain personalized culture information. It extracts meta data for each web page(culture news, culture performance, culture exhibition), perform semantic search and compute result ranking point to base user profile. In order to work efficient, Culture Finder uses five major technique: Machine learning technique for generating user profile from user search behavior and meta data repository, an efficient semantic search system for semantic web agent, query analysis for representing query and query result, personalized ranking method to provide suitable search result to user, upper ontology for generating meta data. In this paper, we also present the structure used in the Culture Finder to support personalized search service.