User Profile Features Research Articles

Optimizing user profile matching: a text-based approach

The rapid expansion of social media platforms has made linking user profiles across various networks an essential aspect of maintaining a consistent identity. With 4.66 billion users reported to be in the Websphere, many are active on multiple social media platforms simultaneously. Identifying users across multiple platforms poses challenges in integrating user profiles from various sources. Different matching schemes have been suggested over the years based on different user profile features, but very little information has been uncovered about user-generated text as a unique attribute for user profile matching, which generally poses real challenges in real-world scenarios. As many users have insufficient text and the use of non-discrete text information makes the comparison operation between the two social networks of quadratic complexity. Our study examines the different existing literature schemes for matching user profile pairs based only on their generated textual content. We suggest and evaluate the effectiveness of a two stage matching approach based on Locality Sensitive Hashing clustering and nearest neighbor search. We also present other matching results of different user representations language models and matching schemes.

Caught in the Lifelong Learning Maze: Helping People with Learning Analytics and Chatbots to Find Personal Career Paths

Current lifelong learning platforms offer users a query option to select a wide variety of courses. However, finding a suitable course among the seemingly endless catalogs of options presented by the platforms is not straightforward. We argue that digital counseling can enhance this process. In this paper, we present a set of three formative studies where we explored the main aspects that can provide the counseling needed. The methods comprise an analysis of user profile characteristics and learning analytics indicators (e.g., learning progress/self-regulation) by means of an expert workshop, evaluating the feasibility of current technologies (e.g., natural language processing) for automatically assessing users' competencies, and a survey on the use of Chatbots as the interaction interface between the users and the lifelong learning portals. The analysis resulted in the extraction of basic requirements for digital counseling. We conclude the paper by presenting a system design derived from these studies.

Deception detection on social media: A source-based perspective

Fast, open, free, and accessible, online social networks are massively used to share news and various information. Unfortunately, their explosive growth amplifies the dissemination of misinformation, posing a severe threat to our societies. Nowadays, it is also a home ground for wrongdoers to spread fake news, rumors, conspiracies, hoaxes, and other forms of deception. Therefore, there is an urgent need to deploy efficient algorithms to tackle this infodemic. Current research focuses mainly on the news content or context to tell the difference between what is credible and what is not. Content-based methods concentrate on detecting the false knowledge the message carries in its writing style. Context-based methods rely on their propagation patterns or the credibility of their source. Finally, some hybrid methods combine these various types. This paper proposes a source-based method in a machine learning framework. It focuses on the profile and the interactions of the news spreaders. Thus, On Twitter, we associate each news article with the interaction network formed by the authors of tweets and their first-degree ego network. Experiments are conducted on two real-world datasets publicly available, covering different domains (Politifact, GossipCop). We select the most diversified news to assess the performance of various machine learning approaches. We conduct an extensive investigation to choose the best network and user-profile features and the most effective machine learning model that can classify news with the highest accuracy. The most effective set of features is well-balanced. It includes four network features and four user-profile parameters. Results show that the “XG Boost” model outperforms its alternatives. (Random Forest, Decision Tree, Multi-Layer Perceptron, K- Nearest Neighbor, Support Vector Machine). It achieves 92% and 91% accuracy on the Politifact and GossipCop datasets. Comparisons with baselines covering a large spectrum of solutions demonstrate its superiority. The proposed solution is promising. Indeed, it requires limited information with few news articles for training. Furthermore, it can detect deception in its initial stage.

Semantic Term-Term Coupling based Feature Enhancement of User Profiles in Recommendation Systems

Content-based recommender system is a subclass of information systems that recommends an item to the user based on its description. It suggests items such as news, documents, articles, webpages, journals, and more to users as per their inclination by comparing the key features of the items with key terms or features of user interest profiles. This paper proposes the new methodology using Non-IIDness based semantic term-term coupling from the content referred by users to enhance recommendation results. In the proposed methodology, the semantic relationship is analyzed by estimating the explicit and implicit relationship between terms. It associates terms that are semantically related in real world or are used inter-changeably such as synonyms. The underestimated features of user profiles have been enhanced after term-term relation analysis which results in improved similarity estimation of relevant items with the user profiles.The experimentation result proves that the proposed methodology improves the overall search and retrieval results as compared to the state-of-art algorithms.

Role of twitter user profile features in retweet prediction for big data streams.

To study the various factors influencing the process of information sharing on Twitter is a very active research area. This paper aims to explore the impact of numerical features extracted from user profiles in retweet prediction from the real-time raw feed of tweets. The originality of this work comes from the fact that the proposed model is based on simple numerical features with the least computational complexity, which is a scalable solution for big data analysis. This research work proposes three new features from the tweet author profile to capture the unique behavioral pattern of the user, namely “Author total activity”, “Author total activity per year”, and “Author tweets per year”. The features set is tested on a dataset of 100 million random tweets collected through Twitter API. The binary labels regression gave an accuracy of 0.98 for user-profile features and gave an accuracy of 0.99 when combined with tweet content features. The regression analysis to predict the retweet count gave an R-squared value of 0.98 with combined features. The multi-label classification gave an accuracy of 0.9 for combined features and 0.89 for user-profile features. The user profile features performed better than tweet content features and performed even better when combined. This model is suitable for near real-time analysis of live streaming data coming through Twitter API and provides a baseline pattern of user behavior based on numerical features available from user profiles only.

MGAT-ESM: Multi-channel graph attention neural network with event-sharing module for rumor detection

Rumor detection is increasingly important in we-media. Most existing rumor detection models focus on mining features of text content, user profiles and propagation patterns. However, these models lack an efficient way to integrate information from multiple resources and have poor performance or low generalization on unseen data because they tend to capture event-specific features contained in visible data. In this study, we propose an end-to-end Multi-channel Graph ATtention network with Event-Sharing Module named MGAT-ESM. First, we parallelly build three subgraphs to model the propagation structures of source tweets and their responses, the relationships of source tweets and their words, and those of source tweets and their related users, respectively. We then design a path embedding method to learn the semantic information of propagation structures, and use graph attention neural network as a backbone to learn the representations of the other two subgraphs, and then aggregate the embedding representations of these three-channel subgraphs with attention mechanism. Moreover, for learning event-invariant features in different rumors, we add an event-sharing module to the backbone network. Finally, we combine the learnt event-invariant features with the aggregated representations to get the final predictions. Experiments on two real-world benchmarks demonstrate that MGAT-ESM achieves the state-of-the-art performance.

A Systematic Literature Review of Anti-Discrimination Design Strategies in the Digital Sharing Economy

Applications of the Digital Sharing Economy (DSE), such as Uber, Airbnb, and TaskRabbit, have become a main facilitator of economic growth and shared prosperity in modern-day societies. However, recent research has revealed that the participation of minority groups in DSE activities is often hindered by different forms of bias and discrimination. Evidence of such behavior has been documented across almost all domains of DSE, including ridesharing, lodging, and freelancing. However, little is known about the underlying design decisions of DSE platforms which allow certain demographics of the market to gain unfair advantage over others. To bridge this knowledge gap, in this paper, we systematically synthesize evidence from 58 interdisciplinary studies to identify the pervasive discrimination concerns affecting DSE platforms along with their triggering features and mitigation strategies. Our objective is to consolidate such interdisciplinary evidence from a software design point of view. Our results show that existing evidence is mainly geared towards documenting and mitigating issues of racism and sexism affecting platforms of ridesharing, lodging, and freelancing. Our review further shows that discrimination concerns in the DSE market are commonly enabled by features of user profiles and commonly impact reputation systems.

Semantic Term-Term Coupling-Based Feature Enhancement of User Profiles in Recommendation Systems

Content-based recommender system is a subclass of information systems that recommends an item to the user based on its description. It suggests items such as news, documents, articles, webpages, journals, and more to users as per their inclination by comparing the key features of the items with key terms or features of user interest profiles. This paper proposes the new methodology using Non-IIDness based semantic term-term coupling from the content referred by users to enhance recommendation results. In the proposed methodology, the semantic relationship is analyzed by estimating the explicit and implicit relationship between terms. It associates terms that are semantically related in real world or are used inter-changeably such as synonyms. The underestimated features of user profiles have been enhanced after term-term relation analysis which results in improved similarity estimation of relevant items with the user profiles.The experimentation result proves that the proposed methodology improves the overall search and retrieval results as compared to the state-of-art algorithms.

Spam detection on Twitter using a support vector machine and users’ features by identifying their interactions

Spam tweets might cause numerous problems for users. An automatic method is introduced as a proposed method to detect spam tweets. This method is based on pre-processing and feature extraction steps. The pre-processing step is significant for our problem due to the specific structure of tweets. The pre-processing step is performed in such a way that after which only the words remain in each tweet that can play a key role in determining whether the tweet is spam or non-spam. In the proposed method, the features are classified into five classes of user profile features, account information features, user activity based features, user interaction based features, and tweet content-based features including 28 different features. In the feature selection step, an optimal subset of these features is selected for the learning process. However, a support vector classifier is used for the learning process by two Gaussian and polynomial kernels. Finally, the proposed method is compared with multi-layer perceptron (MLP), Naive Bayes (NB), random forest (RF), and k-nearest neighbors (KNN) methods in terms of standard criteria. The obtained results show the superiority of the proposed method using support vector machine (SVM) algorithm and polynomial kernel with 0.988 precision, 0.953 efficiency, 0.96 accuracy, F-0.969, and 0.985 ROC area under the curve compared to the other methods, indicating that the proposed method has better performance overall.

Complex Network and Source Inspired COVID-19 Fake News Classification on Twitter

In COVID-19 related infodemic, social media becomes a medium for wrongdoers to spread rumors, fake news, hoaxes, conspiracies, astroturf memes, clickbait, satire, smear campaigns, and other forms of deception. It puts a tremendous strain on society by damaging reputation, public trust, freedom of expression, journalism, justice, truth, and democracy. Therefore, it is of paramount importance to detect and contain unreliable information. Multiple techniques have been proposed to detect fake news propagation in tweets based on tweets content, propagation on the network of users, and the profile of the news generators. Generating human-like content allows deceiving content-based methods. Network-based methods rely on the complete graph to detect fake news, resulting in late detection. User profile-based techniques are effective for bots or fake accounts detection. However, they are not suited to detect fake news from original accounts. To deal with the shortcomings in existing methods, we introduce a source-based method focusing on the news propagators’ community, including posters and re-tweeters to detect such contents. Propagators are connected using follower-following relations. A feature set combining the connectivity patterns of news propagators with their profile features is used in a machine learning framework to perform binary classification of tweets. Complex network measures and user profile features are also examined separately. We perform an extensive comparative analysis of the proposed methodology on a real-world COVID-19 dataset, exploiting various machine learning and deep learning models at the community and node levels. Results show that hybrid features perform better than network features and user features alone. Further optimization demonstrates that Ensemble’s boosting model CATBoost and deep learning model RNN are the most effective, with an AUC score of 98%. Furthermore, preliminary results show that the proposed solution can also handle fake news in the political and entertainment domain using a small training set.

Towards Emotion-aware Recommender Systems: an Affective Coherence Model based on Emotion-driven Behaviors

Decision making is the cognitive process of identifying and choosing alternatives based on preferences, beliefs, and degree of importance given by the decision maker to objects or actions. For instance, choosing which movie to watch is a simple, small-sized decision-making process. Recommender systems help people to make this kind of choices, usually by computing a short list of suggestions that reduces the space of possible options. These systems are strongly based on the knowledge of user preferences but, in order to fully support people, they should be grounded on a holistic view of the user behavior, that includes also how emotions, mood, and personality traits influence her choosing patterns.In this work, we investigate how to include emotional aspects in the recommendation process. We suggest that the affective state of the user, defined by a set of emotions (e.g., joy, surprise), constitutes part of choosing situation that should be taken into account when modeling user preferences.The main contribution of the paper is a general emotion-aware computational model based on affective user profiles in which each preference, such as a 5-star rating on a movie, is associated with the affective state felt by the user at the time when that preference was collected.The model estimates whether an unseen item is suitable for the current affective state of the user, by computing an affective coherence score that takes into account both the affective user profile and not-affective item features. The approach has been implemented into an Emotion-aware Music Recommender System, whose effectiveness has been assessed by performing in-vitro experiments on two benchmark datasets. The main outcome is that our system showed improved accuracy of recommendations compared to baselines which include no affective information in the recommendation model.

Towards the development of a hotel-based e-bike rental service: Results from a stated preference survey and techno-economic analysis

Holiday cycling refers to the occasional use of bicycle during holidays as an alternative mode of transportation for exploring a destination, comprising a promising line of business for rental services of both conventional and electric bicycles (e-bikes), not only in countries with well-established cycling culture, but also in other tourist destinations. This paper advances the notion that a hotel-based e-bike rental service significantly contributes to the guests’ perception on the environmental quality and friendliness of the hotel, particularly if the e-bikes are powered by renewable energy sources, as a tourism product offering in the context of sustainable mobility. To that end, the present work employs a stated preference survey among hotel guests in the city of Mons, Belgium, to capture and analyze the user profile characteristics and preferences. Based on the survey results, it simulates two alternative implementations of the e-bike charging station with a well-established energy systems analysis tool and evaluates the techno-economic feasibility of the proposed service under different usage and pricing scenarios. The findings of this work show that all scenarios lead to positive internal rate of return and return on investment, rendering the proposed e-bike rental service a promising business venture.

Heterogeneous Ensemble Structure based Universal Spam Profile Detection System for Social Media Networks

The exponential rise in internet technology and online social media networks have revitalized human-being to connect and socialize globally irrespective of geographical and any demographic boundaries. Additionally, it has revitalized business communities to reach target audiences through social media networks. However, as parallel adverse up-surge the ever-increasing presence of malicious users or spam has altered predominant intend of such social media network by propagating biased contents, malicious contents and fraud acts. Avoiding and neutralizing such malefic users on social media network has remained a critical challenge due to gigantically large size and user’s diversity such as Facebook, Twitter, and LinkedIn etc. Though exploiting certain user’s behavior and content types can help identifying malicious users, majority of the existing methods are limited due to confined parametric assessment, and inferior classification approaches. With intend to provide spam profile detection system in this paper a novel heterogeneous ensemble-based method is developed. The proposed model exploits user profile features, user’s activity features, location features and content features to perform spam user profile detection. To ensure optimality of computational significances, we applied multi-phased feature selection method employing Wilcoxon Rank Sum test, Significant Predictor test, and Pearson Correlation test, which assured retaining optimal feature sets for further classification. Subsequently, applying an array of machine learning methods, including Logistic regression, decision tree, Support Vector Machine variants with Linear, Polynomial and RBF kernels, Least Square SVM with linear, polynomial and RBF kernels, ANN with different kernels, etc we constituted a robust ensemble model for spam user profile classification. Simulations revealed that the proposed ensemble classification model achieves accuracy and F-score higher than 98%, which is the highest amongst major works done so far. It affirms suitability and robustness of the proposed model for real time spam profile detection and classification on social media platforms.

(Un)Trendy Japan: Twitter bots and the 2017 Japanese general election

Abstract Social networking services (SNSs) can significantly impact public life during important political events. Thus, it comes as no surprise that different political actors try to exploit these online platforms for their benefit. Bots constitute a popular tool on SNSs that appears to be able to shape public opinion and disrupt political processes. However, the role of bots during political events in a non-Western context remains largely under-studied. This article addresses the question of the involvement of Twitter bots during electoral campaigns in Japan. In our study, we collected Twitter data over a fourteen-day period in October 2017 using a set of hashtags related to the 2017 Japanese general election. Our dataset includes 905,215 tweets, 665,400 of which were unique tweets. Using a supervised machine learning approach, we first built a custom ensemble classification model for bot detection based on user profile features, with an area under curve (AUC) for the test set of 0.998. Second, in applying our model, we estimate that the impact of Twitter bots in Japan was minor overall. In comparison with similar studies conducted during elections in the US and the UK, the deployment of Twitter bots involved in the 2017 Japanese general election seems to be significantly lower. Finally, given our results on the level of bots on Twitter during the 2017 Japanese general election, we provide various possible explanations for their underuse within a broader socio-political context.

Analysis of potential demand and costs for the business development of an electric vehicle sharing service

Nowadays combining electro-mobility with carsharing services that shift private mobility from ownership to service use is viewed as the most promising line of business in sustainable transportation for the next years. In this direction, the present paper focuses on the development of an electric vehicle sharing (EVS) service that integrates various options in the vehicle fleet, namely 2-seat and 4-/5-seat electric cars, as well as electric bikes and electric scooters/motorcycles. Using the members of an academic community as the target users, it examines the potential demand and costs for the development of the business case, starting from the quantification of the user base to the analysis of initial investment cost. To this end, this work employs a population study and a stated preference survey to capture the mobility needs and identify the user profile characteristics and preferences, providing thus useful insight on the implementation of the envisaged system. Based on well-defined criteria, it presents the selected locations of the vehicle pick-up/drop-off points and the composition of the electric vehicle fleet. It further proposes a design of the central charging station as the coordinative center of the service and provides a detailed analysis of the infrastructure and fleet purchase costs.

Personal photograph collections ontology development through thematic tags

Purpose- The number and the variety of photos have grown to a great extent as they can be created anytime, everywhere and spontaneously. Searching for a particular photo file has become a boring, repetitive and tedious activity. The application of an ontology to express the user profile characteristics relation with the narrative, spatial, time and other types of information of the collected photos becomes imperative.Design/methodology/approach -The work presented in our article includes the development of a personal photograph collections ontology (MyOntoPhotos) specialising in documenting the metadata of the topics that end-users prefer mostly to capture with their devices. An extensive survey, among 650 participants, was conducted with the use of an online questionnaire comprised of semi-closed questions, following the Likert scale and the scale category grading.Findings -The ontology created was based on the results of an extensive survey aiming to identify thematic areas of interest, apart from spatial and temporal information, as other similar efforts did in the past. It is mentionable that the survey results proved the majority of the responders selected 22 thematic tags.Originality/value - Based on the research findings an innovative concept for a mobile application is presented, focusing on enhancing end-users photo collections organizing and retrieval functions.

Application of the Information Bottleneck method to discover user profiles in a Web store

ABSTRACTThe paper deals with the problem of discovering groups of Web users with similar behavioral patterns on an e-commerce site. We introduce a novel approach to the unsupervised classification of user sessions, based on session attributes related to the user click-stream behavior, to gain insight into characteristics of various user profiles. The approach uses the agglomerative Information Bottleneck (IB) algorithm. Based on log data for a real online store, efficiency of the approach in terms of its ability to differentiate between buying and non-buying sessions was validated, indicating some possible practical applications of the our method. Experiments performed for a number of session samples showed that the method is capable of separating both types of sessions to a large extent. A detailed analysis was performed for the number of clusters ranging from two to seven, and the results were compared to those achieved by applying the most common clustering algorithm, k-means. Increasing the number of clusters generally leads to better results for both algorithms. However, IB demonstrated much higher average efficiency than k-means for the corresponding number of clusters, and this superiority was especially clear for lower number of clusters. The IB-based division of user sessions into seven clusters gives the mean entropy value of 0.28, which means the 95% separation of sessions of both types. Furthermore, a big advantage of our approach is that it gives a possibility to analyze the probability distribution of session attributes in individual clusters, which allows one to discover hidden knowledge about common characteristics of various user profiles and use this knowledge to support managerial decisions.

Aspects of User Profiling in Computer-based Health Information Tailoring Systems: A Narrative Review

Introduction:
 The recent shift from the conventional physician-centered approach to the more polpular approach that with the focuse on patient as the center of healthcare, emphaizes on the critical role of informing and educating patients. Studies shown that tailoring health information to the needs of individuals is more effective than generic materials. Recent improvements in the fields of computer science and Information Communication Technology have made it possible to computerize such an adaptation process. Information tailoring systems use an internal representation of user conditions and needs, which is referred to as a “user model” or “user profile.”
 A user profile represents the system’s beliefs about the user. Hence, it may simply contain demographic information or sophisticated factors such as the state of the disease, user’s attitude, interest, preference, and knowledge. The user profile is known as the basis for designing other system components and has a great impact on the acceptance of the system by the user and the quality of the tailored information.
 To the best of our knowledge, no studies have been conducted so far to analyze and classify user profile aspects and characteristics. In this systematic narrative review, we aim to provide aspects of profiling in health information tailoring systems based on literature from different disciplines.
 Methods:
 comprehensive searches of the PubMed and Scopus databases have been conducted. We searched among English papers with publishing dates ranging from 1990 onward; since that is when computer-tailoring first appeared within the literature. we have devised a list of terms pertinent to the main concepts of computer-tailoring and used a qualitative–interpretive approach for data extraction.
 Results:
 Analyzing the data from 32 eligible studies, we found three aspects in designing a tailoring user profile. Each aspect with its characteristics are provided below:
 1-Identifying common factors used in profiles and classifying these factors thematically, which has three attributes:
 
 The number of factors used to design the user profile and their diversity (e.g. demographic,clinical,behavioral information, learning style and so forth)
 The approaches used to Identify effective factors in tailoring (e.g. evidence-based, avalible data sources)
 Attributes of the factors (e.g. long-term/short-term, static/dynamic)
 
 2-Data collection tools and methods, which has two attributes:
 
 Data collection methods (e.g. explicit, implicit, mixed)
 Assessment tool (e.g. questionnaire, patient record)
 
 3-Data interpretation that demonstrates to what extent the collected data needs to be analyzed to use in tailoring.
 we have also identified two main approaches regarding tailoring: public health and computational tailoring. Public Health communication researcher has relied greatly on health behavior models but generally has used simpler technological approaches, whereas computer science employed more advanced technological approaches but integrated behavior theory to a lesser extent. These two approaches complete each other to provide the necessary requirements for designing a practical tailoring system in future studies.
 Conclusion: In this study we investigate different aspects of designing a user profile in health information tailoring systems. The proposed model is a valuable guide for new researchers in the field. Results from this review provide a comprehensive overview of the field and will help researchers to combine effective methods from across the disciplines in future research.

SybilTrap: A graph‐based semi‐supervised Sybil defense scheme for online social networks

SummarySybil attacks are increasingly prevalent in online social networks. A malicious user can generate a huge number of fake accounts to produce spam, impersonate other users, commit fraud, and reach many legitimate users. For security reasons, such fake accounts have to be detected and deactivated immediately. Various defense schemes have been proposed to deal with fake accounts. However, most identify fake accounts using only the structure of social graphs, leading to poor performance. In this paper, we propose a new and scalable defense scheme, SybilTrap. SybilTrap uses a semi‐supervised technique that automatically integrates the underlying features of user activities with the social structure into one system. Unlike other machine learning–based approaches, the proposed defense scheme works on unlabeled data, and it is effective in detecting targeted attacks, because it manipulates different levels of features of user profiles. We evaluate SybilTrap on a dataset collected from Twitter. We show that our proposed scheme is able to accurately detect Sybil nodes as well as huge conspiracies among them.

Geographic variability of Twitter usage characteristics during disaster events

Twitter is a well-known microblogging platform for rapid diffusion of views, ideas, and information. During disasters, it has widely been used to communicate evacuation plans, distribute calls for help, and assist in damage assessment. The reliability of such information is very important for decision-making in a crisis situation, but also difficult to assess. There is little research so far on the transferability of quality assessment methods from one geographic region to another. The main contribution of this research is to study Twitter usage characteristics of users based in different geographic locations during disasters. We examine tweeting activity during two earthquakes in Italy and Myanmar. We compare the granularity of geographic references used, user profile characteristics that are related to credibility, and the performance of Naïve Bayes models for classifying Tweets when used on data from a different region than the one used to train the model. Our results show similar geographic granularity for Myanmar and Italy earthquake events, but the Myanmar earthquake event has less information from locations nearby when compared to Italy. Additionally, there are significant and complex differences in user and usage characteristics, but a high performance for the Naïve Bayes classifier even when applied to data from a different geographic region. This research provides a basis for further research in credibility assessment of users reporting about disasters