Telematics and Informatics最新文献

英文中文

Who wants to be a YouTuber? Personality traits predict the desire to become a social media influencer

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-06 DOI: 10.1016/j.tele.2025.102248

Michal Misiak , Arkadiusz Urbanek , Tomasz Frackowiak , Piotr Sorokowski

The rise of social media influencing as a career path has sparked both public interest and concern, particularly regarding young people's aspirations. This study investigated how personality traits influence the motivation to become a social media influencer among young adults in Poland (n = 362) and the United Kingdom (n = 411). We examined the Big Five personality traits, narcissism, and histrionism as potential predictors of influencer career aspirations. Participants (N = 773, aged 16–17) completed personality assessments and rated their motivation to pursue various professions. Hierarchical regression analyses revealed that higher levels of extraversion, narcissism, and histrionism were positively associated with motivation to become a social media influencer, while conscientiousness exhibited an inconsistent negative association. Country-specific analyses indicated that narcissism was a significant predictor in Poland, whereas extraversion, conscientiousness, and histrionism were significant predictors in the UK. These findings highlight the interplay between personality and career aspirations in the digital age. While pursuing influencer careers may offer opportunities for self-expression that appeal to certain personality types, it also poses psychological risks, particularly for individuals high in narcissism and histrionism. These results have implications for career counselling and mental health professionals, supporting young adults navigating the new professional landscape.

{"title":"Who wants to be a YouTuber? Personality traits predict the desire to become a social media influencer","authors":"Michal Misiak , Arkadiusz Urbanek , Tomasz Frackowiak , Piotr Sorokowski","doi":"10.1016/j.tele.2025.102248","DOIUrl":"10.1016/j.tele.2025.102248","url":null,"abstract":"<div><div>The rise of social media influencing as a career path has sparked both public interest and concern, particularly regarding young people's aspirations. This study investigated how personality traits influence the motivation to become a social media influencer among young adults in Poland (n = 362) and the United Kingdom (n = 411). We examined the Big Five personality traits, narcissism, and histrionism as potential predictors of influencer career aspirations. Participants (N = 773, aged 16–17) completed personality assessments and rated their motivation to pursue various professions. Hierarchical regression analyses revealed that higher levels of extraversion, narcissism, and histrionism were positively associated with motivation to become a social media influencer, while conscientiousness exhibited an inconsistent negative association. Country-specific analyses indicated that narcissism was a significant predictor in Poland, whereas extraversion, conscientiousness, and histrionism were significant predictors in the UK. These findings highlight the interplay between personality and career aspirations in the digital age. While pursuing influencer careers may offer opportunities for self-expression that appeal to certain personality types, it also poses psychological risks, particularly for individuals high in narcissism and histrionism. These results have implications for career counselling and mental health professionals, supporting young adults navigating the new professional landscape.</div></div>","PeriodicalId":48257,"journal":{"name":"Telematics and Informatics","volume":"98 ","pages":"Article 102248"},"PeriodicalIF":7.6,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nurture over nature? The effects of inferred personality traits and structural social capital on individual resilience

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-04 DOI: 10.1016/j.tele.2025.102249

Fengjiao Zhang , Zhao Pan , Bingli Luo , Qian Hu

Due to increasing pressures from work, family, and society, mental health problems have become an urgent challenge in recent years. Individual resilience—a person’s capacity to cope with considerable change, adversity, or risk—can help decrease the likelihood of mental health problems and recover to a healthy state quickly. Despite its importance for individuals’ mental health, resilience has not received enough attention in the literature. Therefore, using the Myers-Briggs Type Indicator (MBTI), we aim to investigate the influence of personality traits on individual resilience in the mental health context. Meanwhile, based on trait activation theory, we consider the structural social capital as a trait-relevant situational cue and explore its moderating effect on the relationship between personality traits and individual resilience. We trained a deep learning model to infer a user’s personality traits from user-generated textual content, constructed a rule-based algorithm to evaluate individual resilience, and used social network analysis to measure structural social capital. And then we tested our hypotheses using a pooled regression model based on panel data. The results indicated that higher individual resilience is related to higher extroversion, feeling, and perceiving relevant personality traits. Introverts and judgers become more resilient when structural social capital is present. Our findings reveal the important role that personality traits (nature) and structural social capital (nurture) play in shaping and influencing individual resilience. The study offers valuable insights for community managers to identify potential users with low levels of resilience and give them extra care and help.

{"title":"Nurture over nature? The effects of inferred personality traits and structural social capital on individual resilience","authors":"Fengjiao Zhang , Zhao Pan , Bingli Luo , Qian Hu","doi":"10.1016/j.tele.2025.102249","DOIUrl":"10.1016/j.tele.2025.102249","url":null,"abstract":"<div><div>Due to increasing pressures from work, family, and society, mental health problems have become an urgent challenge in recent years. Individual resilience—a person’s capacity to cope with considerable change, adversity, or risk—can help decrease the likelihood of mental health problems and recover to a healthy state quickly. Despite its importance for individuals’ mental health, resilience has not received enough attention in the literature. Therefore, using the Myers-Briggs Type Indicator (MBTI), we aim to investigate the influence of personality traits on individual resilience in the mental health context. Meanwhile, based on trait activation theory, we consider the structural social capital as a trait-relevant situational cue and explore its moderating effect on the relationship between personality traits and individual resilience. We trained a deep learning model to infer a user’s personality traits from user-generated textual content, constructed a rule-based algorithm to evaluate individual resilience, and used social network analysis to measure structural social capital. And then we tested our hypotheses using a pooled regression model based on panel data. The results indicated that higher individual resilience is related to higher extroversion, feeling, and perceiving relevant personality traits. Introverts and judgers become more resilient when structural social capital is present. Our findings reveal the important role that personality traits (nature) and structural social capital (nurture) play in shaping and influencing individual resilience. The study offers valuable insights for community managers to identify potential users with low levels of resilience and give them extra care and help.</div></div>","PeriodicalId":48257,"journal":{"name":"Telematics and Informatics","volume":"98 ","pages":"Article 102249"},"PeriodicalIF":7.6,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Overloaded yet addicted? A meta-analysis of the outcomes of social media overload

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-03 DOI: 10.1016/j.tele.2025.102247

Olli Tyrväinen , Henri Pirkkalainen , Markus Salo , Heikki Karjaluoto

This meta-analysis advances the understanding of social media overload’s dimensions and outcomes. Drawing from the transactional view of technostress and the theory on self-regulation, it theorizes the role played by four dimensions of social media overload —information, social, communication, and system feature overload. Linked to exhaustion and addiction, these dimensions affect self-regulation. Although exhaustion reduces work performance and increases the intention to discontinue social media use, addiction decreases the discontinuance intention and hinders work performance. The study contributes to the information systems literature with an improved understanding of the relation between two literature streams—technostress and information technology addiction.

引用次数: 0

Artificial humanity: A multi-method exploration of user responses to AI influencer affordances in short video platform

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-02 DOI: 10.1016/j.tele.2025.102245

Crystal T. Lee , Yung-Cheng Shen

The advent of social media has led to the emergence of AI influencers. However, research on how affordances by AI influencers shape consumer perceptions remains limited. We addressed this gap by conducting a text-mining analysis of 12,467 user comments on social media related to AI influencers. In addition, we surveyed 978 followers of AI influencers, employing structural equation modeling (SEM) to delineate the affordances of AI influencers. The thematic analysis extracted four key AI affordances, namely modality, autonomy, guidance, and interactivity, that positively shape AI influencers’ perceived humanness and trust, which in-turn drives purchase intention and active engagement. These findings offer multi-method evidence on how the strategic use of AI affordances shapes consumer perceptions and behaviors in human-AI interactions.

引用次数: 0

How emojis and relationships shape sarcasm perception in computer-mediated communication

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-01 DOI: 10.1016/j.tele.2025.102242

Qiaoyi Xue , Yu-Chi Lee

Previous studies have reported that the ‘Wink’ emoji

is considered an effective indicator of sarcasm in computer-mediated communication. However, few studies have compared the effects of different emojis on perceptions of sarcasm and available information about how emojis and relationships jointly affect perceptions of sarcasm. Thus, this study investigates how emojis and sender-receiver relationships influence the perception of sarcasm in ambiguous texts, whether positive or negative. A total of 127 Chinese participants rated sarcasm, unfriendliness, and humour across 36 communication scenarios (six emojis × three relationships × two sentence valences). The three-way analysis of variance results indicated that the use of the ‘Unamused’ emoji

significantly affects the sarcasm perception and emotional responses to ambiguous text replies, where it is an effective indicator of sarcastic criticism. The use of the ‘Wink’ emoji

affects sarcasm perceptions and emotional responses to ambiguous messages. In Eastern cultures, using a ‘Wink’ emoji

in positive ambiguous replies tends to reduce the sarcastic tone, which contrasts with the findings from Western contexts. The ‘Tears of joy’

, ‘Smirk’

, and ‘Smiling’

emojis provide only limited enhancement, resulting in ambiguous interpretations. In addition, the effects of relationship and sentence valence were significant for emotional perception. These findings may support clearer communication and more harmonious relationships.

以往的研究表明，在以计算机为媒介的交流中，"眨眼 "表情符号被认为是讽刺意味的有效指标。然而，很少有研究比较过不同表情符号对讽刺感知的影响，也很少有研究提供关于表情符号和人际关系如何共同影响讽刺感知的信息。因此，本研究探讨了表情符号和发件人与收件人之间的关系如何影响对含混文本中讽刺意味的感知，无论是正面的还是负面的。共有 127 名中国受试者对 36 个交流场景（6 个表情符号 × 3 种关系 × 2 种句子价值）中的讽刺、不友好和幽默进行了评分。三因素方差分析结果表明，使用 "不开心 "表情符号会显著影响对暧昧文本回复的讽刺感知和情绪反应，它是讽刺性批评的有效指标。眨眼 "表情符号的使用会影响对含糊信息的讽刺感知和情感反应。在东方文化中，在正面的模棱两可的回复中使用 "眨眼 "表情符号往往会减少讽刺的语气，这与西方的研究结果形成了鲜明的对比。喜极而泣"、"傻笑 "和 "微笑 "表情符号只能提供有限的增强效果，从而导致模棱两可的解释。此外，关系和句子效价对情绪感知的影响也很显著。这些发现可能有助于更清晰的沟通和更和谐的关系。

{"title":"How emojis and relationships shape sarcasm perception in computer-mediated communication","authors":"Qiaoyi Xue , Yu-Chi Lee","doi":"10.1016/j.tele.2025.102242","DOIUrl":"10.1016/j.tele.2025.102242","url":null,"abstract":"<div><div>Previous studies have reported that the ‘Wink’ emoji <figure><img></figure> is considered an effective indicator of sarcasm in computer-mediated communication. However, few studies have compared the effects of different emojis on perceptions of sarcasm and available information about how emojis and relationships jointly affect perceptions of sarcasm. Thus, this study investigates how emojis and sender-receiver relationships influence the perception of sarcasm in ambiguous texts, whether positive or negative. A total of 127 Chinese participants rated sarcasm, unfriendliness, and humour across 36 communication scenarios (six emojis × three relationships × two sentence valences). The three-way analysis of variance results indicated that the use of the ‘Unamused’ emoji <figure><img></figure> significantly affects the sarcasm perception and emotional responses to ambiguous text replies, where it is an effective indicator of sarcastic criticism. The use of the ‘Wink’ emoji <figure><img></figure> affects sarcasm perceptions and emotional responses to ambiguous messages. In Eastern cultures, using a ‘Wink’ emoji <figure><img></figure> in positive ambiguous replies tends to reduce the sarcastic tone, which contrasts with the findings from Western contexts. The ‘Tears of joy’ <figure><img></figure>, ‘Smirk’<figure><img></figure>, and ‘Smiling’ <figure><img></figure>emojis provide only limited enhancement, resulting in ambiguous interpretations. In addition, the effects of relationship and sentence valence were significant for emotional perception. These findings may support clearer communication and more harmonious relationships.</div></div>","PeriodicalId":48257,"journal":{"name":"Telematics and Informatics","volume":"97 ","pages":"Article 102242"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The pursuit of online misinformation literacy: Understanding age-varying competence for misinformation recognition

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-01 DOI: 10.1016/j.tele.2024.102228

Junyeong Lee , Jung Lee , Jinyoung Min

Addressing online misinformation has become increasingly critical due to the widespread use of the Internet and social media. However, studies show conflicting results regarding competencies in recognizing misinformation across different age groups; thus, initiatives for misinformation literacy have not been as effective as anticipated. To reconcile this conflict and provide a strategy for supporting misinformation literacy, this study aims to explore how perceived competence in recognizing misinformation—comprising confidence and endeavor —varies among age groups and what factors influence this competence. Using data from a media panel survey in South Korea involving 9,060 participants, we found that younger adults exhibit higher confidence and endeavors in recognizing misinformation compared to older adults. Additionally, factors such as smart device usage capability and critical attitudes toward media content significantly influence misinformation recognition across all age groups, with varying impacts. Notably, social media use has contrasting effects as it decreases younger adults’ confidence and endeavors in misinformation recognition but enhances older adults’ confidence. Our findings provide key insights into the age-specific challenges and factors shaping misinformation literacy, emphasizing the importance of tailored educational programs that consider the diverse needs and behaviors of various age groups. These insights can help enhance the effectiveness of misinformation literacy initiatives in the digital age.

{"title":"The pursuit of online misinformation literacy: Understanding age-varying competence for misinformation recognition","authors":"Junyeong Lee , Jung Lee , Jinyoung Min","doi":"10.1016/j.tele.2024.102228","DOIUrl":"10.1016/j.tele.2024.102228","url":null,"abstract":"<div><div>Addressing online misinformation has become increasingly critical due to the widespread use of the Internet and social media. However, studies show conflicting results regarding competencies in recognizing misinformation across different age groups; thus, initiatives for misinformation literacy have not been as effective as anticipated. To reconcile this conflict and provide a strategy for supporting misinformation literacy, this study aims to explore how perceived competence in recognizing misinformation—comprising confidence and endeavor —varies among age groups and what factors influence this competence. Using data from a media panel survey in South Korea involving 9,060 participants, we found that younger adults exhibit higher confidence and endeavors in recognizing misinformation compared to older adults. Additionally, factors such as smart device usage capability and critical attitudes toward media content significantly influence misinformation recognition across all age groups, with varying impacts. Notably, social media use has contrasting effects as it decreases younger adults’ confidence and endeavors in misinformation recognition but enhances older adults’ confidence. Our findings provide key insights into the age-specific challenges and factors shaping misinformation literacy, emphasizing the importance of tailored educational programs that consider the diverse needs and behaviors of various age groups. These insights can help enhance the effectiveness of misinformation literacy initiatives in the digital age.</div></div>","PeriodicalId":48257,"journal":{"name":"Telematics and Informatics","volume":"97 ","pages":"Article 102228"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trust in AI chatbots: A systematic review 对人工智能聊天机器人的信任：系统回顾

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-01 DOI: 10.1016/j.tele.2025.102240

Sheryl Wei Ting Ng , Renwen Zhang

Advancements in artificial intelligence (AI) have enabled increasingly natural and human-like interactions with conversational agents (chatbots). However, the processes and outcomes of trust in AI chatbots remain underexplored. This study provides a systematic review of how trust in AI chatbots is defined, operationalised, and studied, synthesizing factors influencing trust development and its outcomes. An analysis of 40 articles revealed notable variations and inconsistencies in trust conceptualisations and operationalisations. Predictors of trust are categorized into five groups: user, machine, interaction, social, and context-related factors. Trust in AI chatbots leads to diverse outcomes that span affective, relational, behavioural, cognitive, and psychological domains. The review underscores the need for longitudinal studies to better understand the dynamics and boundary conditions of trust development. These findings offer valuable insights for advancing human–machine communication (HMC) research and informing the design of trustworthy AI systems.

人工智能（AI）的进步使人们与对话代理（聊天机器人）之间的互动越来越自然，越来越像人与人之间的互动。然而，人工智能聊天机器人的信任过程和结果仍未得到充分探索。本研究对如何定义、操作和研究人工智能聊天机器人中的信任进行了系统回顾，综合了影响信任发展及其结果的因素。对 40 篇文章的分析表明，信任概念和操作方法存在明显的差异和不一致。信任的预测因素分为五类：用户、机器、交互、社会和情境相关因素。对人工智能聊天机器人的信任会导致情感、关系、行为、认知和心理领域的各种结果。综述强调了进行纵向研究的必要性，以便更好地了解信任发展的动态和边界条件。这些发现为推进人机交流（HMC）研究和设计值得信赖的人工智能系统提供了宝贵的见解。

引用次数: 0

Unpacking cyberchondria: The roles of online health information seeking, health information overload, and health misperceptions

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-01 DOI: 10.1016/j.tele.2024.102225

Xiaoya Yang , Chen Luo , Yimeng Xu , Yifei He , Ruhan Zhao

Cyberchondria, the excessive search for health information online coupled with elevated health anxiety or concerns, has garnered growing scholarly attention recently. Anchored by the S-O-R (Stimulus-Organism-Response) model and information science literature, this study theorizes a pathway from online health information seeking via diverse sources (“S”) to cyberchondria (“R”) through health information overload and misperceptions (“O”). Structural equation modeling based on an online survey (N = 690) disclosed that health information overload was positively associated with searching for health information on online search engines and news media. Additionally, seeking health information from health-specific websites and online news media was positively tied to health misperceptions. Furthermore, increased health information overload was related to stronger health misperceptions, and they were both positively tied to cyberchondria. Theoretically, this study affords a more nuanced understanding of cyberchondria by zooming into the roles of seeking health information via different online sources. Besides, health misperceptions, as a relatively innovative predictor of cyberchondria, have been examined empirically. Practically, the findings furnish feasible strategies to optimize online platforms to mitigate the undesirable consequences of online health information consumption.

{"title":"Unpacking cyberchondria: The roles of online health information seeking, health information overload, and health misperceptions","authors":"Xiaoya Yang , Chen Luo , Yimeng Xu , Yifei He , Ruhan Zhao","doi":"10.1016/j.tele.2024.102225","DOIUrl":"10.1016/j.tele.2024.102225","url":null,"abstract":"<div><div>Cyberchondria, the excessive search for health information online coupled with elevated health anxiety or concerns, has garnered growing scholarly attention recently. Anchored by the S-O-R (Stimulus-Organism-Response) model and information science literature, this study theorizes a pathway from online health information seeking via diverse sources (“S”) to cyberchondria (“R”) through health information overload and misperceptions (“O”). Structural equation modeling based on an online survey (<em>N</em> = 690) disclosed that health information overload was positively associated with searching for health information on online search engines and news media. Additionally, seeking health information from health-specific websites and online news media was positively tied to health misperceptions. Furthermore, increased health information overload was related to stronger health misperceptions, and they were both positively tied to cyberchondria. Theoretically, this study affords a more nuanced understanding of cyberchondria by zooming into the roles of seeking health information via different online sources. Besides, health misperceptions, as a relatively innovative predictor of cyberchondria, have been examined empirically. Practically, the findings furnish feasible strategies to optimize online platforms to mitigate the undesirable consequences of online health information consumption.</div></div>","PeriodicalId":48257,"journal":{"name":"Telematics and Informatics","volume":"97 ","pages":"Article 102225"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analyzing media bias in defense and foreign affairs: A deep learning and eXplainable artificial intelligence approach

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-01 DOI: 10.1016/j.tele.2024.102227

Jungkyun Lee , Min Su Park , Eunil Park

This study aims to investigate media bias in news articles related to defense and foreign affairs by applying deep learning models and eXplainable artificial intelligence (XAI) techniques. We collected and analyzed seven, representing five major Korean media outlets, from conservative and liberal perspectives. The objective is to classify political bias and identify the specific words that contribute to this classification. We employed the BERT-base model from the Korean Language Understanding Evaluation and used local interpretable model-agnostic explanations for a comprehensive analysis. Our methodology achieved a remarkable accuracy of 98.2% in classifying the political bias of news articles, demonstrating the model’s effectiveness. The findings revealed distinct biases in coverage and statements across the media outlets: conservative outlets were more likely to emphasize threats and use singular references, while liberal outlets preferred peaceful and inclusive language. This study provides valuable insights into how the political biases of news media influence both the topics covered and the language used, even within the same category and time frame, ultimately shaping public perception.

本研究旨在通过应用深度学习模型和可扩展人工智能（XAI）技术，调查与国防和外交事务相关的新闻文章中的媒体偏见。我们从保守派和自由派的角度收集并分析了代表韩国五大媒体的七篇文章。我们的目标是对政治偏见进行分类，并找出促成这种分类的特定词语。我们采用了韩国语言理解评估（Korean Language Understanding Evaluation）中的 BERT 基础模型，并使用本地可解释的模型对立解释进行综合分析。我们的方法在对新闻文章的政治偏见进行分类时达到了 98.2% 的高准确率，证明了该模型的有效性。研究结果表明，各媒体在报道和声明方面存在明显的偏见：保守派媒体更倾向于强调威胁和使用单一的提法，而自由派媒体则更倾向于使用和平和包容的语言。这项研究提供了宝贵的见解，让我们了解新闻媒体的政治偏见如何影响报道的主题和使用的语言，甚至在同一类别和时间范围内，最终影响公众的看法。

{"title":"Analyzing media bias in defense and foreign affairs: A deep learning and eXplainable artificial intelligence approach","authors":"Jungkyun Lee , Min Su Park , Eunil Park","doi":"10.1016/j.tele.2024.102227","DOIUrl":"10.1016/j.tele.2024.102227","url":null,"abstract":"<div><div>This study aims to investigate media bias in news articles related to defense and foreign affairs by applying deep learning models and eXplainable artificial intelligence (XAI) techniques. We collected and analyzed seven, representing five major Korean media outlets, from conservative and liberal perspectives. The objective is to classify political bias and identify the specific words that contribute to this classification. We employed the BERT-base model from the Korean Language Understanding Evaluation and used local interpretable model-agnostic explanations for a comprehensive analysis. Our methodology achieved a remarkable accuracy of 98.2% in classifying the political bias of news articles, demonstrating the model’s effectiveness. The findings revealed distinct biases in coverage and statements across the media outlets: conservative outlets were more likely to emphasize threats and use singular references, while liberal outlets preferred peaceful and inclusive language. This study provides valuable insights into how the political biases of news media influence both the topics covered and the language used, even within the same category and time frame, ultimately shaping public perception.</div></div>","PeriodicalId":48257,"journal":{"name":"Telematics and Informatics","volume":"97 ","pages":"Article 102227"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Is the period really “pissed”? The effect of punctuation and message length on perceptions in digital communication 句号真的 "生气 "了吗？标点符号和信息长度对数字通信感知的影响

IF 7.6 2区管理学 Q1 INFORMATION SCIENCE & LIBRARY SCIENCE

Telematics and Informatics

Pub Date : 2025-02-01 DOI: 10.1016/j.tele.2025.102241

Nenagh Kemp , Rebecca Kovacic , Elisabeth Beyersmann

Including a period at the end of a one-word text message (“yes.”) can elicit perceptions of insincerity and negativity. We assessed whether these negative perceptions would hold in longer messages. Australian undergraduates (N = 200) read 30 fictitious message exchanges; positive, neutral, or negative in valence. Exchanges ended in a short (one word), medium (three to four words), or long (six to eight words) message; half with a final period, half without. Participants rated how they thought the friend felt about their message, on a 7-point scale. Across valences, messages with a period were rated more negatively than those without, as were both short and medium messages. In long messages, the period’s presence or absence did not significantly affect ratings. The results imply that this punctuation mark can convey emotional or grammatical information, depending on message length. The findings have implications for the way people compose and interpret digital messages.

引用次数: 0

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Telematics and Informatics

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀