Due to the rapid expansion of the Internet of Vehicles (IoVs), service providers deploy roadside units (RSUs), and base stations (BSs) close to vehicles. They can provide vehicles with computational offloading services quickly. In the context of vehicle social networks, where vehicles can communicate and share data with each other, the security and efficiency of data distribution are crucial. Unfortunately, the open nature of RSU BSs makes them vulnerable to malicious attackers, hence affecting the quality of the user experience. This article proposes a security trust degree incentive-based evaluation mechanism that calculates the security trust degree of vehicle users to RSU BSs through the continuous interaction between them in order to effectively address the aforementioned issues. Additionally, taking into account the competitive nature of task computation offloading between vehicle users and BSs, a stable matching algorithm is used to match each vehicle user with the most appropriate BS so that they can work together to prevent competition in task offloading and improve task offloading efficiency. Due to the limited number of BS matches and the dynamic position changes of vehicle users, we further increase the data distribution efficiency by calculating the vehicle user degree of relationship and connection probability to match vehicle users with similar preferences. Finally, our proposed scheme is validated via numerous simulations with enhanced security service performance in terms of vehicle task offloading, while data distribution efficiency are effectively improved.
{"title":"Interaction Trust-Driven Data Distribution for Vehicle Social Networks: A Matching Theory Approach","authors":"Tengfei Cao;Jie Yi;Xiaoying Wang;Han Xiao;Changqiao Xu","doi":"10.1109/TCSS.2023.3343084","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3343084","url":null,"abstract":"Due to the rapid expansion of the Internet of Vehicles (IoVs), service providers deploy roadside units (RSUs), and base stations (BSs) close to vehicles. They can provide vehicles with computational offloading services quickly. In the context of vehicle social networks, where vehicles can communicate and share data with each other, the security and efficiency of data distribution are crucial. Unfortunately, the open nature of RSU BSs makes them vulnerable to malicious attackers, hence affecting the quality of the user experience. This article proposes a security trust degree incentive-based evaluation mechanism that calculates the security trust degree of vehicle users to RSU BSs through the continuous interaction between them in order to effectively address the aforementioned issues. Additionally, taking into account the competitive nature of task computation offloading between vehicle users and BSs, a stable matching algorithm is used to match each vehicle user with the most appropriate BS so that they can work together to prevent competition in task offloading and improve task offloading efficiency. Due to the limited number of BS matches and the dynamic position changes of vehicle users, we further increase the data distribution efficiency by calculating the vehicle user degree of relationship and connection probability to match vehicle users with similar preferences. Finally, our proposed scheme is validated via numerous simulations with enhanced security service performance in terms of vehicle task offloading, while data distribution efficiency are effectively improved.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141319636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-03DOI: 10.1109/TCSS.2023.3330293
Ivan Conjeaud;Philipp Lorenz-Spreen;Argyris Kalogeratos
This article investigates how interacting agents arrive to a consensus or a polarized state. We study the opinion formation process under the effect of a global steering mechanism (GSM), which aggregates the opinion-driven stochastic agent states at the network level and feeds back to them a form of global information. We also propose a new two-layer agent-based opinion formation model, called GSM-DeGroot , that captures the coupled dynamics between agent-to-agent local interactions and the GSM's steering effect. This way, agents are subject to the effects of a DeGroot-like local opinion propagation, as well as to a wide variety of possible aggregated information that can affect their opinions, such as trending news feeds, press coverage, polls, elections, etc. Contrary to the standard DeGroot model, our model allows polarization to emerge by letting agents react to the global information in a stubborn differential way. Moreover, the introduced stochastic agent states produce event stream dynamics that can fit to real event data. We explore numerically the model dynamics to find regimes of qualitatively different behavior. We also challenge our model by fitting it to the dynamics of real topics that attracted the public attention and were recorded on Twitter. Our experiments show that the proposed model holds explanatory power, as it evidently captures real opinion formation dynamics via a relatively small set of interpretable parameters.
{"title":"DeGroot-Based Opinion Formation Under a Global Steering Mechanism","authors":"Ivan Conjeaud;Philipp Lorenz-Spreen;Argyris Kalogeratos","doi":"10.1109/TCSS.2023.3330293","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3330293","url":null,"abstract":"This article investigates how interacting agents arrive to a consensus or a polarized state. We study the opinion formation process under the effect of a global steering mechanism (GSM), which aggregates the opinion-driven stochastic agent states at the network level and feeds back to them a form of global information. We also propose a new two-layer agent-based opinion formation model, called \u0000<italic>GSM-DeGroot</i>\u0000, that captures the coupled dynamics between agent-to-agent local interactions and the GSM's steering effect. This way, agents are subject to the effects of a DeGroot-like local opinion propagation, as well as to a wide variety of possible aggregated information that can affect their opinions, such as trending news feeds, press coverage, polls, elections, etc. Contrary to the standard DeGroot model, our model allows polarization to emerge by letting agents react to the global information in a stubborn differential way. Moreover, the introduced stochastic agent states produce event stream dynamics that can fit to real event data. We explore numerically the model dynamics to find regimes of qualitatively different behavior. We also challenge our model by fitting it to the dynamics of real topics that attracted the public attention and were recorded on Twitter. Our experiments show that the proposed model holds explanatory power, as it evidently captures real opinion formation dynamics via a relatively small set of interpretable parameters.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141319658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The technological and online experiences of billions worldwide are dominated by a handful of companies known as “Big Tech.” Despite this being a cause for concern in governmental, economic, and ethical spheres, the literature lacks a study exploring the impact of public scandals on, and the global sentiment toward, Big Tech. Here, we quantify the power of Big Tech by analyzing their acquisitions, market capitalization, and number of monthly active users. Moreover, we utilize the synthetic control method to estimate the effect of public scandals on the stock price of two Big Tech companies, and find that they had no lasting effect. We also analyze the number of tweets mentioning these scandals, and find that they quickly fade from the spotlight. To explore public sentiment, we survey 5300 participants across 25 countries, and find that those from countries with lower digital literacy and more authoritarian regimes are more trusting of Big Tech. Furthermore, we find that one in three feels they lack control over the data collected about them, and one in four feels that Big Tech knows what they are thinking, knows more about them than their best friend, and may even be secretly listening to their conversations. Additionally, one in four feels addicted to Big Tech products, have no choice but to use them, and wishes there were more companies to choose from. These findings highlight the adverse effect of the oligopolistic nature of Big Tech on consumer choice and help inform policy-makers aiming to curb their dominance.
{"title":"Big Tech Dominance Despite Global Mistrust","authors":"Hazem Ibrahim;Mikolaj Debicki;Talal Rahwan;Yasir Zaki","doi":"10.1109/TCSS.2023.3339183","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3339183","url":null,"abstract":"The technological and online experiences of billions worldwide are dominated by a handful of companies known as “Big Tech.” Despite this being a cause for concern in governmental, economic, and ethical spheres, the literature lacks a study exploring the impact of public scandals on, and the global sentiment toward, Big Tech. Here, we quantify the power of Big Tech by analyzing their acquisitions, market capitalization, and number of monthly active users. Moreover, we utilize the synthetic control method to estimate the effect of public scandals on the stock price of two Big Tech companies, and find that they had no lasting effect. We also analyze the number of tweets mentioning these scandals, and find that they quickly fade from the spotlight. To explore public sentiment, we survey 5300 participants across 25 countries, and find that those from countries with lower digital literacy and more authoritarian regimes are more trusting of Big Tech. Furthermore, we find that one in three feels they lack control over the data collected about them, and one in four feels that Big Tech knows what they are thinking, knows more about them than their best friend, and may even be secretly listening to their conversations. Additionally, one in four feels addicted to Big Tech products, have no choice but to use them, and wishes there were more companies to choose from. These findings highlight the adverse effect of the oligopolistic nature of Big Tech on consumer choice and help inform policy-makers aiming to curb their dominance.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10379489","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1109/TCSS.2023.3338691
Muhammad Ali;Anwar Said;Iqra Safder;Saeed Ul Hassan;Naif Radi Aljohani;Mudassir Shabbir
Graph representation methods have recently become the de facto standard for downstream machine learning tasks on graph-structured data and have found numerous applications, e.g., drug discovery & development, recommendation, and forecasting. However, the existing methods are specially designed to work in a centralized environment, which limits their applicability to small or medium-sized graphs. In this work, we present a graph embedding method that extracts graph representations in a distributed environment with independent and parallel machines. The proposed method is built-upon the existing approach, distributed graph statistical distance (DGSD), to enhance the scalability on large graphs. The key innovation of our work lies in the proposition of a batching mechanism for client-server message passing, which reduces communication overhead during the computation of the distance matrix. In addition, we present a sampling approach for computing pairwise distances between the nodes to compute the desired graph embedding. Moreover, we systematically explore six distinct variations of a distributed graph embeddings and subsequently subject them to comprehensive evaluation. Our extensive evaluations on over 20 graph datasets and ten baseline methods demonstrate improved running time and comparative classification accuracy compared to state-of-the-art embedding techniques.
{"title":"MSDGSD: A Scalable Graph Descriptor for Processing Large Graphs","authors":"Muhammad Ali;Anwar Said;Iqra Safder;Saeed Ul Hassan;Naif Radi Aljohani;Mudassir Shabbir","doi":"10.1109/TCSS.2023.3338691","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3338691","url":null,"abstract":"Graph representation methods have recently become the de facto standard for downstream machine learning tasks on graph-structured data and have found numerous applications, e.g., drug discovery & development, recommendation, and forecasting. However, the existing methods are specially designed to work in a centralized environment, which limits their applicability to small or medium-sized graphs. In this work, we present a graph embedding method that extracts graph representations in a distributed environment with independent and parallel machines. The proposed method is built-upon the existing approach, distributed graph statistical distance (DGSD), to enhance the scalability on large graphs. The key innovation of our work lies in the proposition of a batching mechanism for client-server message passing, which reduces communication overhead during the computation of the distance matrix. In addition, we present a sampling approach for computing pairwise distances between the nodes to compute the desired graph embedding. Moreover, we systematically explore six distinct variations of a distributed graph embeddings and subsequently subject them to comprehensive evaluation. Our extensive evaluations on over 20 graph datasets and ten baseline methods demonstrate improved running time and comparative classification accuracy compared to state-of-the-art embedding techniques.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1109/TCSS.2023.3341910
Amanul Haque;Munindar P. Singh
Political news is often slanted toward its publisher's ideology and seeks to influence readers by focusing on selected aspects of contentious social and political issues. We investigate political slants in news and their influence on readers by analyzing election-related news and readers’ reactions to the news on Twitter. To this end, we collected election-related news from six major U.S. news publishers who covered the 2020 U.S. presidential election. We computed each publisher's political slant based on the favorability of its news toward the two major parties’ presidential candidates. We find that the election-related news coverage shows signs of political slant both in news headlines and on Twitter. The difference in news coverage of the two candidates between the left-leaning ( LEFT ) and right-leaning ( RIGHT ) news publishers is statistically significant. The effect size is larger for the news on Twitter than for headlines. And, news on Twitter expresses stronger sentiments than the headlines. We identify moral foundations in readers’ reactions to the news on Twitter based on the moral foundation theory. Moral foundations in readers’ reactions to LEFT and RIGHT differ statistically significantly, though the effects are small. Further, these shifts in moral foundations differ across social and political issues. User engagement on Twitter is higher for RIGHT than for LEFT . We posit that an improved understanding of slant and influence can enable better ways to combat online political polarization.
{"title":"NewsSlant: Analyzing Political News and Its Influence Through a Moral Lens","authors":"Amanul Haque;Munindar P. Singh","doi":"10.1109/TCSS.2023.3341910","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3341910","url":null,"abstract":"Political news is often slanted toward its publisher's ideology and seeks to influence readers by focusing on selected aspects of contentious social and political issues. We investigate political slants in news and their influence on readers by analyzing election-related news and readers’ reactions to the news on Twitter. To this end, we collected election-related news from six major U.S. news publishers who covered the 2020 U.S. presidential election. We computed each publisher's political slant based on the favorability of its news toward the two major parties’ presidential candidates. We find that the election-related news coverage shows signs of political slant both in news headlines and on Twitter. The difference in news coverage of the two candidates between the left-leaning (\u0000<sc>LEFT</small>\u0000) and right-leaning (\u0000<sc>RIGHT</small>\u0000) news publishers is statistically significant. The effect size is larger for the news on Twitter than for headlines. And, news on Twitter expresses stronger sentiments than the headlines. We identify moral foundations in readers’ reactions to the news on Twitter based on the moral foundation theory. Moral foundations in readers’ reactions to \u0000<sc>LEFT</small>\u0000 and \u0000<sc>RIGHT</small>\u0000 differ statistically significantly, though the effects are small. Further, these shifts in moral foundations differ across social and political issues. User engagement on Twitter is higher for \u0000<sc>RIGHT</small>\u0000 than for \u0000<sc>LEFT</small>\u0000. We posit that an improved understanding of slant and influence can enable better ways to combat online political polarization.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1109/TCSS.2023.3334306
Xiaolong Zheng;Jingyu Li;Mengyao Lu;Fei-Yue Wang
In the past few years, we have witnessed the rapid development and exponential growth of generative artificial intelligence (GAI) technologies including large language models (LLMs)-enabled ChatGPT and peripheral innovations. These technologies are designed to be humanlike intelligence and intuitive by providing direct access to systems using application programming interfaces (APIs). The GAI applications can fundamentally change economic and financial activities, through revolutionizing the ways that humans interact with machines and giving rise to new modes of production and behavior patterns. It is imperative to develop a new research paradigm that is more suitable than the currently dominating conventional research paradigms. This article presents the new paradigm for economic and financial research with GAI, covering the research objectives, scientific data, and models, and explores the underlying impact and perspective that bring to this field. We elaborate on the potential five scenarios including portfolio management, economic and financial prediction, extreme scenario analysis, policy analysis, and financial fraud detection. The new research paradigm with GAI proposed in this article can provide significant insights for a comprehensive understanding of innovation and transformation in this domain.
在过去几年中，我们见证了生成式人工智能（GAI）技术的快速发展和指数级增长，包括支持大型语言模型（LLMs）的 ChatGPT 和外围创新技术。这些技术旨在通过使用应用编程接口（API）直接访问系统，实现类人智能和直观性。GAI 应用可以从根本上改变经济和金融活动，彻底改变人类与机器的交互方式，并催生新的生产模式和行为模式。当务之急是开发一种比目前占主导地位的传统研究范式更适合的新研究范式。本文介绍了利用 GAI 进行经济和金融研究的新范式，涵盖了研究目标、科学数据和模型，并探讨了该范式给这一领域带来的潜在影响和视角。我们阐述了潜在的五种应用场景，包括投资组合管理、经济和金融预测、极端情景分析、政策分析和金融欺诈检测。本文提出的 GAI 新研究范式可为全面了解该领域的创新和变革提供重要见解。
{"title":"New Paradigm for Economic and Financial Research With Generative AI: Impact and Perspective","authors":"Xiaolong Zheng;Jingyu Li;Mengyao Lu;Fei-Yue Wang","doi":"10.1109/TCSS.2023.3334306","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3334306","url":null,"abstract":"In the past few years, we have witnessed the rapid development and exponential growth of generative artificial intelligence (GAI) technologies including large language models (LLMs)-enabled ChatGPT and peripheral innovations. These technologies are designed to be humanlike intelligence and intuitive by providing direct access to systems using application programming interfaces (APIs). The GAI applications can fundamentally change economic and financial activities, through revolutionizing the ways that humans interact with machines and giving rise to new modes of production and behavior patterns. It is imperative to develop a new research paradigm that is more suitable than the currently dominating conventional research paradigms. This article presents the new paradigm for economic and financial research with GAI, covering the research objectives, scientific data, and models, and explores the underlying impact and perspective that bring to this field. We elaborate on the potential five scenarios including portfolio management, economic and financial prediction, extreme scenario analysis, policy analysis, and financial fraud detection. The new research paradigm with GAI proposed in this article can provide significant insights for a comprehensive understanding of innovation and transformation in this domain.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the financial service sector, customer service is the most critical tool for long-term business growth. A financial complaint detection (CD) system could aid in the identification of shortcomings in product features and service delivery. This could further ensure faster resolution of customer complaints and thereby help retain existing clients and attract new ones. Prior research has prioritized only complaint identification and prediction of the corresponding severity levels; the first aim is to categorize a textual element as a complaint or a noncompliant. The other attempts to classify complaints into several severity levels based on the degree of risk the complainant is willing to endure. Identifying the reason or source of a complaint in a text is a significant but underexplored area in natural language processing study. We propose an explainable complaint cause identification approach with a dyadic attention mechanism at the sentence and word levels, enabling it to give varying amounts of emphasis to more and less important information. As the first subtask, the model simultaneously trains CD, sentiment detection, and emotion recognition tasks. Afterwards, we identify the complaint's cause and its severity level. To do this, the causal span annotations for complaint tweets are added to an existing financial complaints corpus. The findings suggest that conventional computing techniques can be adapted to solve extremely relevant new problems, generating novel opportunities for research 1
The code and dataset are available at https://github.com/sarmistha-D/Complaint-HaN
{"title":"Negative Review or Complaint? Exploring Interpretability in Financial Complaints","authors":"Sarmistha Das;Apoorva Singh;Sriparna Saha;Alka Maurya","doi":"10.1109/TCSS.2023.3338357","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3338357","url":null,"abstract":"In the financial service sector, customer service is the most critical tool for long-term business growth. A financial complaint detection (CD) system could aid in the identification of shortcomings in product features and service delivery. This could further ensure faster resolution of customer complaints and thereby help retain existing clients and attract new ones. Prior research has prioritized only complaint identification and prediction of the corresponding severity levels; the first aim is to categorize a textual element as a complaint or a noncompliant. The other attempts to classify complaints into several severity levels based on the degree of risk the complainant is willing to endure. Identifying the reason or source of a complaint in a text is a significant but underexplored area in natural language processing study. We propose an explainable complaint cause identification approach with a dyadic attention mechanism at the sentence and word levels, enabling it to give varying amounts of emphasis to more and less important information. As the first subtask, the model simultaneously trains CD, sentiment detection, and emotion recognition tasks. Afterwards, we identify the complaint's cause and its severity level. To do this, the causal span annotations for complaint tweets are added to an existing financial complaints corpus. The findings suggest that conventional computing techniques can be adapted to solve extremely relevant new problems, generating novel opportunities for research\u0000<xref><sup>1</sup></xref>\u0000<fn><label><sup>1</sup></label><p>The code and dataset are available at <uri>https://github.com/sarmistha-D/Complaint-HaN</uri></p></fn>\u0000.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this article, we present our work in social emotion prediction to online trending topics. While most prior works focus on emotion from writers or the readers’ emotions evoked by news articles, we investigate discussions from massive social media users and explore the public feelings to the online trending topic. We employ user-generated “#hashtags” to indicate online trending topics and construct a large-scale Chinese dataset for social emotion prediction (LCSEP) to trending topics collected from the Chinese microblog Sina Weibo. It contains more than 20 000 trending topics, each with social emotions voted in 24 fine-grained types, and gathers hashtags, posts, comments, and related metadata to give each trending topic a thorough context. We also propose a Hashtag- and Topic-Enhanced Attention Model ( HTEAM ) that combines a pretrained BERT model, a neural topic model, and an attention mechanism via joint training to understand social emotion. Experiments show that HTEAM outperforms baselines and achieves the state-of-the-art result.
{"title":"LCSEP: A Large-Scale Chinese Dataset for Social Emotion Prediction to Online Trending Topics","authors":"Keyang Ding;Chuang Fan;Yiwen Ding;Qianlong Wang;Zhiyuan Wen;Jing Li;Ruifeng Xu","doi":"10.1109/TCSS.2023.3334296","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3334296","url":null,"abstract":"In this article, we present our work in social emotion prediction to online trending topics. While most prior works focus on emotion from writers or the readers’ emotions evoked by news articles, we investigate discussions from massive social media users and explore the public feelings to the online trending topic. We employ user-generated “#hashtags” to indicate online trending topics and construct a large-scale Chinese dataset for social emotion prediction (LCSEP) to trending topics collected from the Chinese microblog Sina Weibo. It contains more than 20 000 trending topics, each with social emotions voted in 24 fine-grained types, and gathers hashtags, posts, comments, and related metadata to give each trending topic a thorough context. We also propose a \u0000<italic>Hashtag- and Topic-Enhanced Attention Model</i>\u0000 (\u0000<sc>HTEAM</small>\u0000) that combines a pretrained BERT model, a neural topic model, and an attention mechanism via joint training to understand social emotion. Experiments show that \u0000<sc>HTEAM</small>\u0000 outperforms baselines and achieves the state-of-the-art result.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-28DOI: 10.1109/TCSS.2023.3338509
Pratima Singh;Amita Jain
Civil unrest is among the important hurdles in the countries’ progress as it deteriorates gross domestic product (GDP), international relations, foreign direct investment (FDI), globalization, public opinion, tourism, and businesses. Due to civil unrest a variety of serious problems, viz. loss of life/injury, resources, political stability, and human rights occur. Recently, few researchers have given insights on the prediction of occurrences of civil unrest events by using hypothesis testing and some basic machine/deep learning models. Important factors such as people’s emotions/sentiments, contextual information, and civil unrest events feature’ importance are ignored presently. For the first time, the proposed work overcomes all these research gaps by hybridizing the neutrosophic set, aspect-based sentiment analysis, particle swarm optimization (PSO), and hierarchical long short-term memory (hierarchical LSTM). Neutrosophic set along with aspect-based sentiment analysis has been used to get the sentiment and features’ importance. The resulting features’ weights have been optimized using PSO. For a more comprehensive understanding of the input sequence and feature weights, hierarchical LSTM has been used. Doing so obtained results that are more accurately improved for civil unrest events prediction. The performance of the proposed model has been evaluated and compared with state of art methods. Experimentation and evaluation show the proposed model outperforms the baseline methods by 3% to 15% on the standard datasets in terms of accuracy.
{"title":"Context-Aware Civil Unrest Event Prediction Using Neutrosophic-Aspect-Based Sentiment Analysis, PSO, and Hierarchical LSTM","authors":"Pratima Singh;Amita Jain","doi":"10.1109/TCSS.2023.3338509","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3338509","url":null,"abstract":"Civil unrest is among the important hurdles in the countries’ progress as it deteriorates gross domestic product (GDP), international relations, foreign direct investment (FDI), globalization, public opinion, tourism, and businesses. Due to civil unrest a variety of serious problems, viz. loss of life/injury, resources, political stability, and human rights occur. Recently, few researchers have given insights on the prediction of occurrences of civil unrest events by using hypothesis testing and some basic machine/deep learning models. Important factors such as people’s emotions/sentiments, contextual information, and civil unrest events feature’ importance are ignored presently. For the first time, the proposed work overcomes all these research gaps by hybridizing the neutrosophic set, aspect-based sentiment analysis, particle swarm optimization (PSO), and hierarchical long short-term memory (hierarchical LSTM). Neutrosophic set along with aspect-based sentiment analysis has been used to get the sentiment and features’ importance. The resulting features’ weights have been optimized using PSO. For a more comprehensive understanding of the input sequence and feature weights, hierarchical LSTM has been used. Doing so obtained results that are more accurately improved for civil unrest events prediction. The performance of the proposed model has been evaluated and compared with state of art methods. Experimentation and evaluation show the proposed model outperforms the baseline methods by 3% to 15% on the standard datasets in terms of accuracy.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-22DOI: 10.1109/TCSS.2023.3334768
Yi Yang;Chen Peng;En-Zhi Cao;Wenxuan Zou
As an emerging technology, the knowledge graph (KG) has been successfully applied in various industries. Though some potential benefits of the KG have been identified, there is still little work on implementing the KG in supply chain risk management (SCRM). This study develops a KG-based risk management framework to improve the resilience of Supply Chains (SCs). Specifically, the construction of the SC knowledge graph (SC-KG) framework, including the implementation steps, is presented in detail for the purpose of SC knowledge retrieval, data visualization analysis, risk monitoring, early warning, and decision support. Furthermore, the SC-KG is well constructed to build a scenario-based SCRM framework under consideration of the severity of disruptions. Especially during long-term disruptions, the continuity of SCs is maintained through the employment of a product change strategy and a structurally scalable and dynamically adapted network design method. The findings of the study are instructive for SC managers in adopting digital technologies for SC mitigation and recovery under disruptions. Finally, a practical SC-KG containing over 2.5 million entities and 11 types of relationships has been developed and its basic functions have been implemented, which contributes to improving the quality of SC management.
{"title":"Building Resilience in Supply Chains: A Knowledge Graph-Based Risk Management Framework","authors":"Yi Yang;Chen Peng;En-Zhi Cao;Wenxuan Zou","doi":"10.1109/TCSS.2023.3334768","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3334768","url":null,"abstract":"As an emerging technology, the knowledge graph (KG) has been successfully applied in various industries. Though some potential benefits of the KG have been identified, there is still little work on implementing the KG in supply chain risk management (SCRM). This study develops a KG-based risk management framework to improve the resilience of Supply Chains (SCs). Specifically, the construction of the SC knowledge graph (SC-KG) framework, including the implementation steps, is presented in detail for the purpose of SC knowledge retrieval, data visualization analysis, risk monitoring, early warning, and decision support. Furthermore, the SC-KG is well constructed to build a scenario-based SCRM framework under consideration of the severity of disruptions. Especially during long-term disruptions, the continuity of SCs is maintained through the employment of a product change strategy and a structurally scalable and dynamically adapted network design method. The findings of the study are instructive for SC managers in adopting digital technologies for SC mitigation and recovery under disruptions. Finally, a practical SC-KG containing over 2.5 million entities and 11 types of relationships has been developed and its basic functions have been implemented, which contributes to improving the quality of SC management.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：