Analyzing User Interactions Research Articles

An automated social media manager based on artificial intelligence

In today's world of social media, where brands and companies constantly interact with their audiences, the automation of content management processes is becoming increasingly important. Manual content creation, publication, and analysis on social networks require significant resources and time. Automated social media management systems based on artificial intelligence help simplify these processes, enhancing efficiency and optimizing audience engagement strategies. Artificial intelligence in social media marketing systems allows for the automation of tasks such as creating text posts, scheduling publications across different platforms, and analyzing user interactions. Artificial intelligence can analyze audience behavior, predict the optimal time for posts, and recommend changes to content strategies for maximum reach. This not only saves time but also improves the effectiveness of marketing campaigns through more accurate analytical data. However, the automation of social media marketing also faces challenges. The primary issues include the complexity of integrating different social networks into a single management system and the limitations in generating high-quality content that meets the emotional and stylistic requirements of the brand. Additionally, a major challenge is content personalization based on data analysis, which must account for each audience segment's unique needs and behavioral characteristics. Despite these challenges, the prospects for developing automated social media marketing managers are promising due to ongoing innovations in artificial intelligence and machine learning. Future research and development will focus on improving the quality of automated content generation, enhancing user interfaces, and integrating new social platforms to expand multi-channel marketing campaign management capabilities. Thus, the automation of social media marketing is a promising field that will enable brands and companies to optimize their audience engagement strategies while significantly reducing the time and resources required for content creation, publication, and analysis. This work presents the structure of the main entities of an automated social media management system based on artificial intelligence, including users, professions, questions, answers, settings, and integration with Telegram. The developed system enables efficient content management, automates publications, and personalizes audience interaction based on user responses. The system's described key components, attributes, and relationships provide scalability and flexibility, allowing brands and companies to optimize their marketing strategies and client interactions.

Integration of Virtual Reality (VR) and Artificial Intelligence (AI) in Autism Therapy

This concept note explores the integration of Virtual Reality (VR) and Artificial Intelligence (AI) in autism therapy, aiming to enhance therapeutic outcomes for children with autism spectrum disorder (ASD). VR provides immersive, controlled environments for practicing social, cognitive, and motor skills, while AI offers personalized, adaptive learning experiences and real-time feedback. The synergy of these technologies promises innovative, effective interventions that cater to the unique needs of each child. This project proposes the development and evaluation of a VR-AI therapy platform, focusing on improving social interaction, communication, and daily living skills among young children with autism. The integration of Virtual Reality (VR) and Artificial Intelligence (AI) into autism therapy offers a transformative approach to enhancing treatment effectiveness and accessibility. Autism Spectrum Disorder (ASD) presents unique challenges in social interaction, communication, and behavior, requiring tailored therapeutic interventions. VR provides immersive environments where individuals with ASD can safely practice social scenarios, sensory processing, and daily living skills. AI, particularly through machine learning algorithms, can personalize these virtual experiences by adapting to the user's progress and specific needs, offering real-time feedback and data-driven insights for therapists. This concept note explores the synergistic potential of combining VR and AI in autism therapy. VR environments can be meticulously controlled and replicated, allowing for consistent therapeutic sessions. AI can analyze user interactions within these environments, providing granular data to refine treatment plans. The integration aims to make therapy more engaging, individualized, and scalable. This approach not only enhances the effectiveness of traditional therapies but also addresses limitations such as therapist availability and the need for generalized settings. Furthermore, this technology-driven paradigm can democratize access to high-quality autism therapy, particularly in underserved regions. The proposed integration of VR and AI heralds a new era in autism therapy, promising improved outcomes and greater inclusivity.

Development of prediction models for thermostat override behavior in direct load control events

Direct load control (DLC) is a prominent solution for demand-side energy management, where utility providers adjust consumers' temperature setpoints through smart thermostats. However, occupant overrides can have a detrimental impact on the overall efficacy of DLC. This study focuses on understanding override mechanisms and occupant responses during DLC. Real-world data from the Ecobee Donate Your Data (DYD) program is used to analyze user interactions with smart thermostats. Through a comprehensive analysis of four types of variables, a decision tree algorithm was found capable of accurately classifying smart thermostat users in terms of their level of compliance with the DLC program. This classification was based on general information accessible through smart thermostats enabling the evaluation of users' potential engagement in DLC without prior DLC experience. Additionally, a clustering algorithm was used to identify three distinct types of DLC participants characterized by their individual thermal comfort preferences and general habits. A predictive model for thermostat override behavior is developed based on the clustering results. These findings contribute to designing targeted and less disruptive DLC strategies that better align with participants' needs and enhance overall DLC effectiveness.

Systemic Literature Review of Recognition-Based Authentication Method Resistivity to Shoulder-Surfing Attacks

The rapid advancement of information technology (IT) has given rise to a new era of efficient and fast communication and transactions. However, the increasing adoption of and reliance on IT has led to the exposure of personal and sensitive information online. Safeguarding this information against unauthorized access remains a persistent challenge, necessitating the implementation of improved computer security measures. The core objective of computer security is to ensure the confidentiality, availability, and integrity of data and services. Among the mechanisms developed to counter security threats, authentication stands out as a pivotal defense strategy. Graphical passwords have emerged as a popular authentication approach, yet they face vulnerability to shoulder-surfing attacks, wherein an attacker can clandestinely observe a victim’s actions. Shoulder-surfing attacks present a significant security challenge within the realm of graphical password authentication. These attacks occur when an unauthorized individual covertly observes the authentication process of a legitimate user by shoulder surfing the user or capturing the interaction through a video recording. In response to this challenge, various methods have been proposed to thwart shoulder-surfing attacks, each with distinct advantages and limitations. This study thus centers on reviewing the resilience of existing recognition-based graphical password techniques against shoulder-surfing attacks by conducting a comprehensive examination and evaluation of their benefits, strengths, and weaknesses. The evaluation process entailed accessing pertinent academic resources through renowned search engines, including Web of Science, Science Direct, IEEE Xplore, ProQuest, Scopus, Springer, Wiley Online Library, and EBSCO. The selection criteria were carefully designed to prioritize studies that focused on recognition-based graphical password methods. Through this rigorous approach, 28 studies were identified and subjected to a thorough review. The results show that fourteen of them adopted registered objects as pass-objects, bolstering security through object recognition. Additionally, two methods employed decoy objects as pass-objects, enhancing obfuscation. Notably, one technique harnessed both registered and decoy objects, amplifying the security paradigm. The results also showed that recognition-based graphical password techniques varied in their resistance to different types of shoulder-surfing attacks. Some methods were effective in preventing direct observation attacks, while others were vulnerable to video-recorded and multiple-observation attacks. This vulnerability emerged due to attackers potentially extracting key information by analyzing user interaction patterns in each challenge set. Notably, one method stood out as an exception, demonstrating resilience against all three types of shoulder-surfing attacks. In conclusion, this study contributes to a comprehensive understanding of the efficacy of recognition-based graphical password methods in countering shoulder-surfing attacks by analyzing the diverse strategies employed by these methods and revealing their strengths and weaknesses.

Comparing the Impact of Social Media Regulations on News Consumption

Users online tend to consume information adhering to their system of beliefs and ignore dissenting information. During the COVID-19 pandemic, users get exposed to a massive amount of information about a new topic having a high level of uncertainty. In this article, we analyze two social media that enforced opposite moderation methods, Twitter and Gab, to assess the interplay between news consumption and content regulation concerning COVID-19. We compare the two platforms on about three million pieces of content, analyzing user interaction with respect to news articles. We first describe users' consumption patterns on the two platforms focusing on the political leaning of news outlets. Finally, we characterize the echo chamber effect by modeling the dynamics of users' interaction networks. Our results show that the presence of moderation pursued by Twitter produces a significant reduction of questionable content, with a consequent affiliation toward reliable sources in terms of engagement and comments. Conversely, the lack of clear regulation on Gab results in the tendency of the user to engage with both types of content, showing a slight preference for the questionable ones which may account for a dissing/endorsement behavior. Twitter users show segregation toward reliable content with a uniform narrative. Gab, instead, offers a more heterogeneous structure where users, independent of their leaning, follow people who are slightly polarized toward questionable news.

Service-Action-Objects

With the diversity of digital platforms available nowadays, captur- ing, integrating, and analyzing user interactions across multiple platforms in a uniform way is critical for determining the over- all system's success. We present recommendations for a cross- platform system for logging interaction data. The ideal logging system should be: expressive, customizable and future-ready, struc- tured and consistent, developer-friendly, unobtrusive, and easy- to-interpret and convey to others. Based on these recommenda- tions we propose Service-Action-Objects, an approach that cap- tures interaction data on each platform as events in the form of a Service, a distinct feature such as a \blog," an Action, an action that a user has performed within the service such as \wrote an article," and Objects, an object or set of objects being acted on by the user such as the identi er of the blog article written. We discuss the strengths and limitations of this approach and present examples.

UX Framework Including Imbalanced UX Dataset Reduction Method for Analyzing Interaction Trends of Agent Systems.

The performance of game AI can significantly impact the purchase decisions of users. User experience (UX) technology can evaluate user satisfaction with game AI by analyzing user interaction input through a user interface (UI). Although traditional UX-based game agent systems use a UX evaluation to identify the common interaction trends of multiple users, there is a limit to evaluating UX data, i.e., creating a UX evaluation and identifying the interaction trend for each individual user. The loss of UX data features for each user should be minimized and reflected to provide a personalized game agent system for each user. This paper proposes a UX framework for game agent systems in which a UX data reduction method is applied to improve the interaction for each user. The proposed UX framework maintains non-trend data features in the UX dataset where overfitting occurs to provide a personalized game agent system for each user, achieved by minimizing the loss of UX data features for each user. The proposed UX framework is applied to a game called "Freestyle" to verify its performance. By using the proposed UX framework, the imbalanced UX dataset of the Freestyle game minimizes overfitting and becomes a UX dataset that reflects the interaction trend of each user. The UX dataset generated from the proposed UX framework is used to provide customized game agents of each user to enhanced interaction. Furthermore, the proposed UX framework is expected to contribute to the research on UX-based personalized services.

A Unified Comparison of User Modeling Techniques for Predicting Data Interaction and Detecting Exploration Bias.

The visual analytics community has proposed several user modeling algorithms to capture and analyze users' interaction behavior in order to assist users in data exploration and insight generation. For example, some can detect exploration biases while others can predict data points that the user will interact with before that interaction occurs. Researchers believe this collection of algorithms can help create more intelligent visual analytics tools. However, the community lacks a rigorous evaluation and comparison of these existing techniques. As a result, there is limited guidance on which method to use and when. Our paper seeks to fill in this missing gap by comparing and ranking eight user modeling algorithms based on their performance on a diverse set of four user study datasets. We analyze exploration bias detection, data interaction prediction, and algorithmic complexity, among other measures. Based on our findings, we highlight open challenges and new directions for analyzing user interactions and visualization provenance.

Analysis of user interaction with virtual objects in augmented reality applications

The paper proposes approaches for analyzing user interaction with augmented reality objects and describes the results obtained from implementing the developed methods for optimal placement of virtual objects in augmented reality applications in practice. A large amount of collected experimental data is statistically analyzed to make sure that the previously proposed method of optimal augmented reality object placement really simplifies the user experience and reduces the time needed for object placement. The results of this analysis allow us to conclude the effectiveness of the proposed method. The current challenges of applications which implement augmented reality technology in the field of user experience and their solutions are also discussed. This research is conducted to find new methods for developing applications and services that present features to the user by applying augmented reality technology. Currently, there are many different algorithms that allow the recognition of anchor points in flat images and in space. However, at a higher level, there are many research tasks for developers on the most effective application of these algorithms and subsequent analysis of the data obtained. The active expansion of augmented reality and its gradual introduction into many areas of human activity is generating new topical challenges, which is the reason for the investigation of the described field in the present article.

Building an Urban Smart Community System Based on Association Rule Algorithms

Intelligent system development is an integral component of smart community development and has a significant impact on the development of smart communities. Some cities continue to implement personalized smart community services, resulting in the formation of smart city communities with unique characteristics. Urban smart communities are based on the principle of owner-occupant convenience, integrating a wealth of community information and making it more relevant to each and every resident through intelligent management. Increasing information transmission rates have enhanced the ability of smart community systems to integrate information, but the smart community recommendation method is still based on traditional categorized recommendations. This paper addresses the deficiency of recommended information in smart urban communities. By analyzing user interaction and operation data, we can determine the interest and recognition of browsing attractions among users. Compared to conventional classification recommendations, weighted association rules can identify potentially very important rules applicable to small groups, thereby meeting the needs of various groups and enabling personalized services. Through continuous feedback from user behavior data, the system gradually identifies the community information that users are interested in during the specific recommendation process. After testing, the smart community system’s recommendation accuracy and real-time performance have vastly improved in comparison to categorical recommendations, and it can effectively meet the needs of tenants for community recommendations.

The Design and Testing of 3DmoveR: an Experimental Tool for Usability Studies of Interactive 3D Maps

Various widely available applications such as Google Earth have made interactive 3D visualizations of spatial data popular. While several studies have focused on how users perform when interacting with these with 3D visualizations, it has not been common to record their virtual movements in 3D environments or interactions with 3D maps. We therefore created and tested a new web-based research tool: a 3D Movement and Interaction Recorder (3DmoveR). Its design incorporates findings from the latest 3D visualization research, and is built upon an iterative requirements analysis. It is implemented using open web technologies such as PHP, JavaScript, and the X3DOM library. The main goal of the tool is to record camera position and orientation during a user’s movement within a virtual 3D scene, together with other aspects of their interaction. After building the tool, we performed an experiment to demonstrate its capabilities. This experiment revealed differences between laypersons and experts (cartographers) when working with interactive 3D maps. For example, experts achieved higher numbers of correct answers in some tasks, had shorter response times, followed shorter virtual trajectories, and moved through the environment more smoothly. Interaction-based clustering as well as other ways of visualizing and qualitatively analyzing user interaction were explored.

A social recommendation method based on the integration of social relationship and product popularity

Abstract Web 2.0 technology fosters the flourishing growth and development of social networks. More and more people are participating in the activities on social networks to interact and share information with each other. Thus, consumers are often making their purchasing decisions based on information from the Internet such as reviews, ratings, and comments on products, especially from their trusted friends. However, a great amount of available information may cause the problem of information overload for consumers. In seeking to attain a good recommendation performance by taking the high-potential factors into account as far as possible, this paper proposes a novel social recommendation method on the basis of the integration of interactions, trust relationships and product popularity to predict user preferences, and recommend relevant products in social networks. In addition, the proposed method mainly focuses on analyzing user interactions to infer their latent interactions in accordance with the user ratings and corresponding reviews. Additionally, users may be affected by the popularity of products, so this factor has also been taken into consideration in this work. The experimental results show that the proposed recommendation method has a better recommendation performance in comparisons to other methods because the proposed method can accurately analyze user preferences and further recommend high-potential products to target users in social networks to support their purchase decision making. Furthermore, the proposed method can not only reduce the time and effort users spend on querying information, but also positively relieve the problem of information overload.

Analyzing User Interactions with Biomedical Ontologies: A Visual Perspective

Biomedical ontologies are large: Several ontologies in the BioPortal repository contain thousands or even hundreds of thousands of entities. The development and maintenance of such large ontologies is difficult. To support ontology authors and repository developers in their work, it is crucial to improve our understanding of how these ontologies are explored, queried, reused, and used in downstream applications by biomedical researchers. We present an exploratory empirical analysis of user activities in the BioPortal ontology repository by analyzing BioPortal interaction logs across different access modes over several years. We investigate how users of BioPortal query and search for ontologies and their classes, how they explore the ontologies, and how they reuse classes from different ontologies. Additionally, through three real-world scenarios, we not only analyze the usage of ontologies for annotation tasks but also compare it to the browsing and querying behaviors of BioPortal users. For our investigation, we use several different visualization techniques. To inspect large amounts of interaction, reuse, and real-world usage data at a glance, we make use of and extend PolygOnto, a visualization method that has been successfully used to analyze reuse of ontologies in previous work. Our results show that exploration, query, reuse, and actual usage behaviors rarely align, suggesting that different users tend to explore, query and use different parts of an ontology. Finally, we highlight and discuss differences and commonalities among users of BioPortal.

Analyzing user interactions with biomedical ontologies: A visual perspective

Biomedical ontologies are large: Several ontologies in the BioPortal repository contain thousands or even hundreds of thousands of entities. The development and maintenance of such large ontologies is difficult. To support ontology authors and repository developers in their work, it is crucial to improve our understanding of how these ontologies are explored, queried, reused, and used in downstream applications by biomedical researchers. We present an exploratory empirical analysis of user activities in the BioPortal ontology repository by analyzing BioPortal interaction logs across different access modes over several years. We investigate how users of BioPortal query and search for ontologies and their classes, how they explore the ontologies, and how they reuse classes from different ontologies. Additionally, through three real-world scenarios, we not only analyze the usage of ontologies for annotation tasks but also compare it to the browsing and querying behaviors of BioPortal users. For our investigation, we use several different visualization techniques. To inspect large amounts of interaction, reuse, and real-world usage data at a glance, we make use of and extend PolygOnto, a visualization method that has been successfully used to analyze reuse of ontologies in previous work. Our results show that exploration, query, reuse, and actual usage behaviors rarely align, suggesting that different users tend to explore, query and use different parts of an ontology. Finally, we highlight and discuss differences and commonalities among users of BioPortal.

Design and Technical Validation of a Telemedicine Service for Rural Healthcare in Ecuador.

Telemedicine is becoming increasingly important in Ecuador, especially in areas such as rural primary healthcare and medical education. Rural telemedicine programs in the country need to be strengthened by means of a technological platform adapted to local surroundings and offering advantages such as access to specialized care, continuing education, and so on, combined with modest investment requirements. This present article presents the design of a Telemedicine Platform (TMP) for rural healthcare services in Ecuador and a preliminary technical validation with medical students and teachers. An initial field study was designed to capture the requirements of the TMP. In a second phase, the TMP was validated in an academic environment along three consecutive academic courses. Assessment was by means of user polls and analyzing user interactions as registered automatically by the platform. The TMP was developed using Web-based technology and open code software. One hundred twenty-four students and 6 specialized faculty members participated in the study, conducting a total of 262 teleconsultations of clinical cases and 226 responses, respectively. The validation results show that the TMP is a useful communication tool for the documentation and discussion of clinical cases. Moreover, its usage may be recommended as a teaching methodology, to strengthen the skills of medical undergraduates. The results indicate that implementing the system in rural healthcare services in Ecuador would be feasible.

Discovering User Behavioral Features to Enhance Information Search on Big Data

Due to the emerging Big Data paradigm, driven by the increasing availability of intelligent services easily accessible by a large number of users (e.g., social networks), traditional data management techniques are inadequate in many real-life scenarios. In particular, the availability of huge amounts of data pertaining to user social interactions, user preferences, and opinions calls for advanced analysis strategies to understand potentially interesting social dynamics. Furthermore, heterogeneity and high speed of user-generated data require suitable data storage and management tools to be designed from scratch. This article presents a framework tailored for analyzing user interactions with intelligent systems while seeking some domain-specific information (e.g., choosing a good restaurant in a visited area). The framework enhances a user's quest for information by exploiting previous knowledge about their social environment, the extent of influence the users are potentially subject to, and the influence they may exert on other users. User influence spread across the network is dynamically computed as well to improve user search strategy by providing specific suggestions, represented as tailored faceted features. Such features are the result of data exchange activity (called data posting) that enriches information sources with additional background information and knowledge derived from experiences and behavioral properties of domain experts and users. The approach is tested in an important application scenario such as tourist recommendation, but it can be profitably exploited in several other contexts, for example, viral marketing and food education.

Exploring the Relationship Between Online Social Network Site Usage and the Impact on Quality of Life for Older and Younger Users: An Interaction Analysis.

BackgroundAnalyzing content generated by users of social network sites has been shown to be beneficial across a number of disciplines. Such analysis has revealed the precise behavior of users that details their distinct patterns of engagement. An issue is evident whereby without direct engagement with end users, the reasoning for anomalies can only be the subject of conjecture. Furthermore, the impact of engaging in social network sites on quality of life is an area which has received little attention. Of particular interest is the impact of online social networking on older users, which is a demographic that is specifically vulnerable to social isolation. A review of the literature reveals a lack of knowledge concerning the impact of these technologies on such users and even less is known regarding how this impact varies across different demographics.ObjectiveThe objective of our study was to analyze user interactions and to survey the attitudes of social network users directly, capturing data in four key areas: (1) functional usage, (2) behavioral patterns, (3) technology, and (4) quality of life.MethodsAn online survey was constructed, comprising 32 questions. Each question directly related to a research question. Respondents were recruited through a variety of methods including email campaigns, Facebook advertisements, and promotion from related organizations.ResultsIn total, data was collected from 919 users containing 446 younger and 473 older users. In comparison to younger users, a greater proportion of older users (289/473, 61.1% older vs 218/446, 48.9% younger) (P<.001) stated that Facebook had either a positive or huge impact on their quality of life. Furthermore, a greater percentage of older users strongly agreed that Facebook strengthened their relationship with other people (64/473, 13.5% older vs 40/446, 9.0%younger) (P=.02). In comparison to younger users, a greater proportion of older users had more positive emotions—classified as slightly better or very good—during their engagement with Facebook (186/473, 39.3% older vs 120/446, 26.9% younger) (P<.001).ConclusionsThe results reveal that despite engaging at considerably lower rates with significantly fewer connections, older users gain a greater quality-of-life benefit. Results disclose how both cohorts vary in their use, interactions, and rationale for engaging with Facebook.

Automatic detection of usability smells in web applications

Abstract Usability assessment of web applications continues to be an expensive and often neglected practice. While large companies are able to spare resources for studying and improving usability in their products, smaller businesses often divert theirs in other aspects. To help these cases, researches have devised automatic approaches for user interaction analysis, and there are commercial services that offer automated usability statistics at relatively low fees. However, most existing approaches still fall short in specifying the usability problems concretely enough to identify and suggest solutions. In this work we describe usability smells of user interaction, i.e., hints of usability problems on running web applications, and the process in which they can be identified by analyzing user interaction events. We also describe USF, the tool that implements the process in a fully automated way with minimum setup effort. USF analyses user interaction events on-the-fly, discovers usability smells and reports them together with a concrete solution in terms of a usability refactoring, providing usability advice for deployed web applications.

Aggregate Profile Clustering for Streaming Analytics

Many analytic applications require analyzing user interaction data. In particular, such data can be aggregated over a window to build user activity profiles. Clustering such aggregate profiles is useful for grouping together users with similar behaviors, so that common models could be built for them. In this paper, we present an approach for clustering profiles that are incrementally maintained over a stream of updates. Owing to the potentially large number of users and high rate of interactions, maintaining profile clusters can have high processing and memory resource requirements. To tackle this problem, we apply distributed stream processing. However, in the presence of distributed state, it is a major challenge to partition the profiles over nodes such that memory and computation balance is maintained, while keeping the clustering accuracy high. Furthermore, in order to adapt to potentially changing user interaction patterns, the partitioning of profiles to nodes should be continuously revised, yet one should minimize the migration of profiles so as not to disturb the online processing of updates. We develop a re-partitioning technique that achieves all these goals. To achieve this, we keep micro-cluster summaries at each node and periodically collect these summaries at a central node to perform re-partitioning. We use a greedy algorithm with novel affinity heuristics to revise the partitioning and update the routing tables without introducing a lengthy pause. We showcase the effectiveness of our approach using an application that clusters customers of a telecommunications company based on their aggregate calling profiles.

Analyzing user interaction with the ViewFinder video retrieval system

AbstractThis study investigates interactive video retrieval. The basis for this study is that user‐ and search task‐centric research in video information retrieval can assist efforts for developing effective user interfaces and help complement the existing corpus of video retrieval research by providing evidence for the benefits of evaluating systems using such an approach. Accordingly, the results were collected and analyzed from the perspective of certain users and search tasks (i.e., information needs). The methodology of this study employed specially designed interactive search experiments to examine a number of different factors in a video retrieval context, including those that correspond to search tasks of a particular domain, interface features and functions, system effectiveness, and user interactions. The results indicated that the use and effectiveness of certain interface features and functions were dependent on the type of search task, while others were more consistent across the full experiment. Also included is a review of prior research pertaining to visual search tasks, systems development, and user interaction. ViewFinder, the prototype system used to carry out the interactive search experiments of this study, is fully described.