Online Users Research Articles

Эвристический потенциал искусственного интеллекта в анализе социальных сетей

Artificial intelligence is an important part of modern life. AI exists to improve lives and free up time and resources for the tasks that require thoughtful human action. The advent of artificial intelligence (AI) created new data analyzing the capabilities of the modern phenomenon of social networking, accurately analyzing and understanding the dynamics of online communities and users` sentiments. AI succeeds in such area as social media. Internet users use social media to communicate, search for information, buy things and even work. Social networks also have a high amount of data that can be used to analyze social processes and people's behavior. However, the amount of data is so large that so its processing and analysis can be a time-consuming process. Artificial intelligence can help to solve this problem. The article is devoted to the study of the role of artificial intelligence in the analysis of social networks, highlights the possibilities of AI and problems, considers various methods of analysis and data collection, such as social listening, natural language processing, as well as an automatic content classification system. The use of a heuristic approach to this issue based on AI helps to significantly speed up the process of data processing and reduce the cost of analysis that would be performed by manual labor. As a result, it was established that artificial intelligence has a great heuristic potential in the analysis of social networks. Its ability to analyze large amount of data, recognize patterns and identify data trends and also automate management tasks makes it a valuable tool for understanding social media trends and users` behavior.

A Deep Learning Framework for Monitoring Audience Engagement in Online Video Events

This paper introduces a deep learning methodology for analyzing audience engagement in online video events. The proposed deep learning framework consists of six layers and starts with keyframe extraction from the video stream and the participants’ face detection. Subsequently, the head pose and emotion per participant are estimated using the HopeNet and JAA-Net deep architectures. Complementary to video analysis, the audio signal is also processed using a neural network that follows the DenseNet-121 architecture. Its purpose is to detect events related to audience engagement, including speech, pauses, and applause. With the combined analysis of video and audio streams, the interest and attention of each participant are inferred more accurately. An experimental evaluation is performed on a newly generated dataset consisting of recordings from online video events, where the proposed framework achieves promising results. Concretely, the F1 scores were 79.21% for interest estimation according to pose, 65.38% for emotion estimation, and 80% for sound event detection. The proposed framework has applications in online educational events, where it can help tutors assess audience engagement and comprehension while hinting at points in their lectures that may require further clarification. It is effective for video streaming platforms that want to provide video recommendations to online users according to audience engagement.

“View and Hide Definitions” of Racist Hate Speech: Ethnophaulisms in Google’s English Dictionary

This paper aims to foster debate about the language of racist hate speech in online English lexicography. For this purpose, it presents a study on the treatment of ethnophaulisms, or ethnic slurs, in “powered by Oxford Languages” Google’s English dictionary. The focus is indeed on the perspective of the general user of the Internet, in light of the connection between two facets of this digital age. The first one is the strong and growing tendency among Internet users to ‘google’ their language issues. The second one is the alarming increase in cases of hate speech online, most of which are based on ethnicity and nationality, according to reports by the United Nations. Consequently, the free and pervasive content of Google’s English dictionary represents a case in point to investigate whether and how online users are warned against the power of these hate words. A selected sample of 285 English ethnic slurs have been looked up in the dictionary and, if recorded, their entries have been scrutinised to identify lexicographic data regarding their semantic relevance and offensiveness. Findings show that the majority are included, they mostly present ethnicity-related senses, but less than half of the total are treated as ethnophaulisms. In this respect, the major dictionary markers indicating offensiveness are effect labels, predominantly alone or combined with definitions. Relative to their size, thus, ethnophaulisms in Google’s English dictionary are clearly described as offensive or derogatory expressions, thus making online users aware of their hurtful nature.

Analyzing fuzzy semantics of reviews for multi-criteria recommendations

Hotel reviews play a vital role in tourism recommender system. They should be analyzed effectively to enhance the accuracy of recommendations which can be generated either from crisp ratings on a fixed scale or real sentiments of reviews. But crisp ratings cannot represent the actual feelings of reviewers. Existing tourism recommender systems mostly recommend hotels on the basis of vague and sparse ratings resulting in inaccurate recommendations or preferences for online users. This paper presents a semantic approach to analyze the online reviews being crawled from tripadvisor.in. It discovers the underlying fuzzy semantics of reviews with respect to the multiple criteria of hotels rather than using the crisp ratings. The crawled reviews are preprocessed via data cleaning such as stopword and punctuation removal, tokenization, lemmatization, pos tagging to understand the semantics efficiently. Nouns representing frequent features of hotels are extracted from pre-processed reviews which are further used to identify opinion phrases. Fuzzy weights are derived from normalized frequency of frequent nouns and combined with sentiment score of all the synonyms of adjectives in the identified opinion phrases. This results in fuzzy semantics which form an ideal representation of reviews for a multi-criteria tourism recommender system. The proposed work is implemented in python by crawling the recent reviews of Jaipur hotels from TripAdvisor and analyzing their semantics. The resultant fuzzy semantics form a manually tagged dataset of reviews tagged with sentiments of identified aspects, respectively. Experimental results show improved sentiment score while considering all the synonyms of adjectives. The results are further used to fine-tune BERT models to form encodings for a query-based recommender system. The proposed approach can help tourism and hospitality service providers to take advantage of such sentiment analysis to examine the negative comments or unpleasant experiences of tourists and making appropriate improvements. Moreover, it will help online users to get better recommendations while planning their trips.

An Automatic Method to Prevent and Classify Cyberbullying Incidents using Machine Learning Approach

The technological advancements and the increasing popularity of social networking platforms, the sharing of personal information among online users has become widespread. This sharing occurs effortlessly through various devices such as computers and mobile phones. Cyberbullying can manifest through SMS, text messages, and various applications, as well as online platforms like social media and forums, where individuals can view, engage with, or distribute content.The project offers a comprehensive understanding of Cyberbullying incidents and their corresponding offences combining a series of approaches reported in relevant Work. The implementation provides the opportunity to systematically combine various element or Cyberbullying characteristics. Additionally, a comprehensive list of Cyberbullying-related offences is put forward. The offenses are ordered in a Deep Neural Network classification system based on specific criteria to assist in better classification and correlation of their respective incidents. This enables a thorough understanding of the repeating and underlying criminal activities. This study focuses on classifying user posts and image content into bullying or non bullying through reputation score

The data acquisition methodology to build the source information base for personnel monitoring (technological approach)

The All-Russia monitoring of the staffing needs in librarianship is an efficient way to get valuable current and prospective data through using the latest technological solutions and efficient interaction between public libraries affiliated with regional/municipal agencies of culture of the Russian Federation constituents.The authors discuss the technology and results of data acquisition, as well as the obtained staff monitoring database. For the first time, the tested method of data acquisition enabled the Russian State Library to monitor the staff needs in librarianship in the multitasking mode and to apply the cloud technology with the professional application designed for online operation on the national scope. The authors explore the differences between national and foreign software providers in rendering specific services to online users. The professional application enabled to conduct monitoring in the shortest term, to optimize expenses and to save resources in complex environment. Among methodological solutions, the Center of Educational Programs Monitoring of the Research Educationa Activities Department of the Russian State Library, have designed the standardized data collection forms for every level of libraries.The effectiveness of this methodology enabled to launch the system of data acquisition for the All-Russian monitoring of staff needs in the library sphere, to systematize data by the RF constituents and as a data set, and to build the source database for staff monitoring in librarianship.

Can User Characteristics Predict Norm Adherence on Social Media? Exploring User-Centric Misinformation Interventions

The work-in-progress explores user-centric misinformation interventions on social media as such tools are limited. Knowledge of relationships between online user characteristics and their expressed adherence to a desired norm (i.e., rejecting misinformation or supporting factual information) is understudied with limited integrated multi-modal machine-learning models to infer demographic and sociopsychological characteristics. Thus, we piloted 9,331 Twitter users tweeting COVID-19 vaccines between May 1, 2020, and April 30, 2021. Employing a CNN-LSTM framework, our model analyzes user biographies, profile images, and pre-COVID historical tweets to infer user traits over 90% accuracy for individual characteristics and an overall accuracy of 85.61%, which outperforms existing tools and other designs. Further, using multi-logistic regression, we identified significant predictors of users' adherence to desired norms, such as gender and pre-pandemic prosocial content engagement, while finding no significant age correlation. Our findings illuminate pathways for targeted misinformation mitigation strategies during critical public health crises.

An Optimized Fraud Identification Framework Using DCNN For Wireless Communication

Convolution Neural Network (Cnn) Is The Powerful Framework To Solve The Lot Of Issues Of Link Detection In Unlabeled Wireless Communication. Last Few Decades Lot Of Fraud Detection Strategies Has Been Projected Bit That All Are Inefficient For Detecting The Frauds. Therefore, The Great Need For Effective And Fast Fraud Detection Scheme With Higher Detection Accuracy. In This Research, Spider Based Convolution Neural Network (Sbcnn) Model To Detect The Frauds In The Wireless Communication. Initially, Create The Wireless Channel To Transmit The Messages From Source To Destination. Here, The Fraudulent Activities Are Detected Based On The Packet Delivery Time Of The Source To Destination Of The Wireless Medium. Moreover, The Proposed System Implementation Is Done In The Matlab Frame Work Additionally; The Obtained Results Are Validated With Prevailing Methods For Evaluating The Efficiency Of The Proposed Sbcnn Approach. Wireless communication fraud poses a significant threat as unauthorized use of services, compromising the security of cellular networks and infrastructure. With the surge in online services and users, the reliance on wireless communication for high-speed internet applications has grown. Despite the convenience brought by technologies like net banking, credit cards, and online services, financial frauds and unauthorized payments remain substantial risks. The intricate nature of wireless communication, illustrated in Fig. 1, where devices use signals between source and destination nodes, leads to challenges like network interference and loss rate, often exacerbated by fraudulent activities. Numerous techniques, including Artificial Intelligence (AI), hybrid ensemble models, oversampling, and machine learning, have been explored but haven't provided satisfactory solutions. In this study, an optimization-assisted intelligent framework is proposed to maximize communication performance, addressing the limitations of existing approaches. The subsequent sections analyse related research, identify issues with conventional methods, elaborate on the functioning of the proposed framework, discuss results, and conclude with research inferences

Are We Really Retaining URiM Faculty in Academic Medicine?

Previous studies have identified the need to improve recruitment and retention of faculty who are underrepresented in medicine (URiM); however, it is unclear to what extent medical schools have been able to sustain growth and retain URiM faculty representation. Numbers of URiM faculty at each AAMC medical school from 2012 to 2021 were obtained from the Association of American Medical Colleges Faculty Administrative Management Online User System database. Year-over-year percent change was calculated for each school and year of the study period for all URiM faculty, junior URiM faculty, and senior URiM faculty. Pearson's correlation was used to compare percent change in 1 year to the previous and subsequent years for all three groups. Pearson's correlation coefficients were also used to compare percent change between junior and senior URiM faculty for the same, previous, and subsequent years. The percentage change for URiM faculty at all ranks between adjacent years occurring from 2012 to 2021 was weakly and negatively associated (r = - 0.06, p value = 0.03). There was significant positive correlation between the percent change in junior URiM faculty and senior URiM faculty in the same year (r = 0.11) and previous year (r = 0.09). URiM faculty growth in 1 year is not sustained in the next year. More research is needed to better understand efforts at retention of URiM faculty in academic medicine.

The Effect of E-service Quality and Customer Satisfaction and Trust to Customer Online Shopping Behavior

China's e-commerce sector is experiencing rapid growth. Among Chinese cities, Beijing stands out with its robust development, consistently ranking among the top three in the nation. Nonetheless, Beijing's e-commerce enterprises encounter various challenges. This research endeavors to examine the interplay between e-service quality, customer satisfaction, trust, and online shopping behavior within the Beijing e-commerce landscape. Descriptive method was considered by the researchers. The respondents of the study are the users of online shopping platforms that operates in Beijing China who have experience using major online consumption platforms. The sample size is 385 people which was calculated by Raosoft software. The respondents of the study were chosen using the simple random sampling design. Moreover, constructed survey questionnaires served as a tool with five-key point Likert scale. The Statistical Package for Social Sciences (SPSS) was employed in the statistical analysis of data. The following statistical tools were used in the study: frequency and percentage, mean, reliability and validity analysis, Analysis of Variance and Multiple Linear Regression. The study resulted in a strong positive relationship between customer satisfaction, trust and over-all e-service quality. Specifically, customer satisfaction and trust resulted in a very strong relationship to customer behaviors. For the comparison of means when grouped according to profile variables, customer satisfaction level and over-all e-service quality have a significant difference when grouped to frequency of purchase. Based on the results of the study, the researchers proposed a development program to help improve the quality of e-services and thus increase customer re-purchase rates.

Video apps user engagement and stock market volatility: Evidence from China

This paper explores the relationship between the user activity of major comprehensive video apps in China and stock market volatility. The online user counts of mainstream video apps can significantly forecast the volatility of the Chinese stock market. Furthermore, integrating these factors demonstrates excellent predictive performance in different horizons. The reliability and consistency of the empirical results are further confirmed by using MCS and DoC tests.

Book Reading and Recommendation Application using Python and Dart

Recommender System are new generation internet tool that help user in navigating through information on the internet and receive information related to their preferences. Most of these existing systems are user-based ratings where content-based and collaborative based learning methods are used. These systems' irrationality is their rating technique, which counts the users who have already been unsubscribed from the services and no longer rate books. This paper proposed an effective system for recommending books for online users that rated a book using the clustering method and then found a similarity of that book to suggest a new book. Inksavor is an innovative book reading and recommendation app that seamlessly integrates Python and Dart technologies to redefine the reading experience. Users can explore a diverse library, read, and actively engage with literature by writing, annotating, and sharing their thoughts. The app offers a user-friendly writing interface, enabling aspiring authors to effortlessly create and share their literary works. Key Words: Contend Based Filtering, collaborative based filtering, K-Nearest Neighbour Algorithm(KNN), Recommendation system

Attention to global warming, consensus transition, and crypto trading

Does public attention to global warming affect crypto trading? We address this question by investigating how Google users' search on global warming is associated with the trading activeness of Ethereum, the second largest cryptocurrency in the world. Exploiting Ethereum's transition to a green blockchain (i.e., “The Merge”), we find that before the transition, Google search on global warming is negatively associated with the transaction volumes of Ethereum, but the relationship turns significantly positive after The Merge, suggesting online users' green orientation towards energy-efficient cryptocurrencies. Our analysis sheds light upon an emerging research on the environmental issues in crypto markets.

A STUDY ON CUSTOMER AWARENESS ON E- BANKING SERVICES AT UNION BANK OF INDIA, MANGALORE

E-banking is fast becoming a norm in the developed world, and is being implemented by many banks in developing economies around the globe. The main reason behind this success is the numerous benefits it can provide, both to the banks and to customers of financial services. For banks, it can provide a cost effective way of conducting business and enriching relationship with customers by offering superior services, and innovative products which may be customized to individual needs. For customers it can provide a greater choice in terms of the channels they can use to conduct their business, and convenience in terms of when and where they can use e- banking. Over the last decade India has been one of the fastest adopters of information technology, particularly because of its capability to provide software solution to organizations around the world. This capability has provided a tremendous impetuous to the domestic banking industry in India to deploy the latest in technology, particularly in the Internet banking and e-commerce areas. Technology is playing a major role in increasing the efficiency, courtesy and speed of customer service. An Online Banking user is expected to perform transactions online such as Checking account balance and transaction history, Paying bills, Transferring funds between accounts, Requesting credit card advances, ordering checks, Managing investments and stocks trading. From a bank‟s perspective, using the Internet is more efficient than using other distribution mediums because banks are looking for an increased customer base. Moreover Internet delivery offers customized service to suit the needs and the likes of each user. Mass customization happens effectively through Online Banking. It reduces cost and replaces time spent on routine errands with spending time on business errands. Online Banking means less staff members, smaller infrastructure demands, compared with other banking channels. From the customers‟ perspective, Online Banking provides a convenient and effective way to manage finances that is easily accessible 24 hours a day, seven days a week. In addition information is up to date. Nevertheless Online Banking has disadvantages for banks like how to work the technology, set- up cost, legal issues, and lack of personal contact with customers. And for customers there are security and privacy issues.

Meat substitutes in Media Discourse

Shifting from meat consumption is critical for future dietary evolution. Mainstream newspapers and social media are the leading platforms for expressing this opinion. By analysing the media discourse, the proponents of the shift from meat, to plant-based meat and cultured meat were identified. The objectives were: a) to identify themes, word frequencies, and sentiment related to meat substitutes, b) to determine Chinese perceptions of the two meat substitutes, and c) to determine which food functions are of concern to Chinese consumers. Between July 2016 and July 2022, the researcher gathered data from People’s Daily and China Daily online outlets and user comments. 574 news articles and 2,345 online comments were extracted. Three techniques were applied: sentiment analysis, thematic analysis, and word cloud analysis. The results revealed that newspapers reported positively on meat substitutes, yet user comments showed negative public perception. Chinese people held positive attitudes toward plant-based meat and negative attitudes toward cultured meat. Thus, the insights from the media discourse provided valuable indicators for stakeholders to develop sustainable food education and consumption strategies.

Multi-Resolution Odd Sketch for Mining Extended Jaccard Similarity of Dynamic Streaming sets

Estimating the Jaccard similarity between two or more streaming sets is a fundamental problem with many applications, such as mining the co-occurrences of host communication behaviors in IP networks and the co-purchasing behaviors of online users in E-commence systems. For a “streaming” data set, its elements arrive sequentially at the stream processing engine, whose working memory is limited in size. To meet the resource constraint, the data set must be stored as a compressed format called a “sketch”, so that millions or even billions of such sets can be held in the memory of the engine. To strike a balance between memory cost and similarity estimation accuracy, many sketching algorithms were proposed, such as MinHash, HyperLogLog and theta sketch. As far as we know, most of previous solutions fail to handle the fully dynamic streaming sets that allow both the insertion and the deletion of elements. Although PCSA <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula> , and virtual odd sketch (VOS) partially solves the deletion problem, their memory efficiency and estimation accuracy can be fundamentally improved. In this paper, we propose a multi-resolution odd sketch (MROS), which allows more accurate similarity estimation with less memory consumption. Its design is to encode a streaming set into multiple layers of odd sketches with exponentially reducing sampling probabilities. No matter a set is small or large, we can pick a suitable sampling probability to accurately estimate its cardinality. Next, we present an algorithm to estimate the extended Jaccard similarity of multiple streaming sets. Their compressed MROS summaries are merged by bitwise XOR, which in turn helps estimate the cardinality of symmetric difference of the multiple sets. Then, using these estimated cardinalities as observations, we estimate the size of an arbitrary set expression, which is connected by union <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\bigcup$</tex-math></inline-formula> , intersection <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\bigcap$</tex-math></inline-formula> , relative complement <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\setminus$</tex-math></inline-formula> , and symmetric difference <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\Delta$</tex-math></inline-formula> . Our evaluation results show that its accuracy outperforms MinHash, KMV, PCSA <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula> and VOS, and it can support element deletion.

“Stuff that only mixed‐race people would understand”: Community and identity‐related experiences in online groups for multiracial people

AbstractMultiracial people are a rapidly growing group who may still lack social support from similar others in their offline lives. This study aimed to understand the user experiences in online groups for multiracial individuals. In a cross‐sectional online survey, 300 multiracial emerging adults (79% women; mean age = 23; most common ethnic identity components: 86% White/European, 44% Chinese, 17% Japanese, 16% Southeast Asian, and 13% Filipino) answered open‐ended questions about their experiences in Facebook groups for multiracial people. Participants described aspects of the groups they liked and disliked most, as well as their identity‐related experiences in the groups. We used reflexive thematic analysis to generate four themes within participants responses: (1) online groups as a gateway into connections with other multiracial individuals, (2) deriving a sense of belonging and community, (3) an opportunity for exploration and validation of racial identity, and (4) negative intrusions such as negative content (e.g., trolling, repetitive posting) and racism. For racial and ethnic minorities such as multiracial individuals, Facebook groups provide a space for community‐building and identity‐related experiences. Although online groups can foster a strong sense of community, validation, and belonging, findings also highlight potential challenges and limitations (e.g., how to delineate group boundaries, difficulty forming close relationships). Online group users and researchers should explore novel ways of maximizing these positive experiences while addressing users' concerns and negative experiences.

Rancangan Strategi Pemasaran Layanan JIMS (Jabarlink Internet Managed Service) di Perhotelan Pangandaran dalam Meningkatan Keunggulan Kompetitif dan Preferensi Tamu

Jabarlink as an ISP (Internet Service Provider) company is known to be active in marketing JIMS (Jabarlink Internet Managed Service) products in the Pangandaran area, but still requires an ideal strategy to be able to market JIMS products which currently have positive potential for hotels that want to increase their competitive advantage and guest preferences. This research aims to design a marketing strategy for JIMS services in Pangandaran hotels to increase competitive advantage and guest preferences. A qualitative method with a descriptive approach has been used where data collection was carried out through interviews with 15 informants / hotel managers, and involving 100 hotel customers in the interview process using an online user questionnaire. This research found that ISP companies such as Jabarlink need to carry out three activities in their marketing process, namely: Product innovation to avoid the threat of substitute products, effective and creative communication, and market segmentation and offering the right price

Research on data preprocessing method for artificial intelligence algorithm based on user online behavior

This paper delves into the significance and efficacy of data preprocessing techniques specifically tailored for user online behavior data in enhancing the performance of artificial intelligence algorithms. Through a comprehensive literature review, we identify gaps and opportunities in current methodologies, setting the stage for the development of a novel data preprocessing approach. This proposed method is meticulously designed to handle the complexities and nuances of user online behavior data. We conduct a series of case studies and rigorous empirical analyses to evaluate the effectiveness of our approach. The results clearly demonstrate that our method substantially improves data quality by effectively reducing noise and eliminating irrelevant information, which, in turn, enhances the overall performance of the AI algorithms. The paper concludes with a discussion on the limitations of the current study and provides insightful directions for future research in the field. This includes potential refinements to the preprocessing technique and its application to other types of behavioral data in different AI domains.

Trust, Social Influence and Perceived Usefulness: Examining Online Purchase Intentions among Gen Z

The growing popularity of online shopping collides with user reservations related to trust, social influence, and perceived purchase usefulness, with such concerns acutely observable among Gen Z populations. As digital natives and prolific online users, Gen Z's purchasing patterns offer valuable insights for marketers adjusting their online strategies. This study extends the body of knowledge by examining the determinants of online purchase intentions among Gen Z thereby guiding university administrators, educators, and online retailers in crafting improved online shopping experiences. Utilizing a non-intrusive, naturalistic research setting, the study harnesses an anonymous survey methodology, and data is rigorously analyzed using Statistical Package for Social Science (SPSS). Findings indicate that trust and perceived usefulness are significantly connected to students' online purchasing decisions. This study enhances the theory of online buying habits by emphasizing trust and value in e-commerce. It advises adding trust cues and functional benefits to online portals, the key to influencing Gen Z buyers and boosting market expansion and e-shopper satisfaction.