Pub Date : 2023-09-23DOI: 10.1007/s13278-023-01124-6
Falah Amro, Hemant Purohit
{"title":"Integrated content-network analysis to discover influential collectives for studying social cyber-threats from online social movements","authors":"Falah Amro, Hemant Purohit","doi":"10.1007/s13278-023-01124-6","DOIUrl":"https://doi.org/10.1007/s13278-023-01124-6","url":null,"abstract":"","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135959676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-22DOI: 10.1007/s13278-023-01125-5
Bernardo Cerqueira de Lima, Renata Maria Abrantes Baracho, Thomas Mandl, Patricia Baracho Porto
Abstract Social media platforms that disseminate scientific information to the public during the COVID-19 pandemic highlighted the importance of the topic of scientific communication. Content creators in the field, as well as researchers who study the impact of scientific information online, are interested in how people react to these information resources. This study aims to devise a framework that can sift through large social media datasets and find specific feedback to content delivery, enabling scientific content creators to gain insights into how the public perceives scientific information, and how their behavior toward science communication (e.g., through videos or texts) is related to their information-seeking behavior. To collect public reactions to scientific information, the study focused on Twitter users who are doctors, researchers, science communicators, or representatives of research institutes, and processed their replies for two years from the start of the pandemic. The study aimed in developing a solution powered by topic modeling enhanced by manual validation and other machine learning techniques, such as word embeddings, that is capable of filtering massive social media datasets in search of documents related to reactions to scientific communication. The architecture developed in this paper can be replicated for finding any documents related to niche topics in social media data.
{"title":"Reactions to science communication: discovering social network topics using word embeddings and semantic knowledge","authors":"Bernardo Cerqueira de Lima, Renata Maria Abrantes Baracho, Thomas Mandl, Patricia Baracho Porto","doi":"10.1007/s13278-023-01125-5","DOIUrl":"https://doi.org/10.1007/s13278-023-01125-5","url":null,"abstract":"Abstract Social media platforms that disseminate scientific information to the public during the COVID-19 pandemic highlighted the importance of the topic of scientific communication. Content creators in the field, as well as researchers who study the impact of scientific information online, are interested in how people react to these information resources. This study aims to devise a framework that can sift through large social media datasets and find specific feedback to content delivery, enabling scientific content creators to gain insights into how the public perceives scientific information, and how their behavior toward science communication (e.g., through videos or texts) is related to their information-seeking behavior. To collect public reactions to scientific information, the study focused on Twitter users who are doctors, researchers, science communicators, or representatives of research institutes, and processed their replies for two years from the start of the pandemic. The study aimed in developing a solution powered by topic modeling enhanced by manual validation and other machine learning techniques, such as word embeddings, that is capable of filtering massive social media datasets in search of documents related to reactions to scientific communication. The architecture developed in this paper can be replicated for finding any documents related to niche topics in social media data.","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136059451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-22DOI: 10.1007/s13278-023-01118-4
Mohammed Alghobiri
{"title":"Exploring the attributes of influential users in social networks using association rule mining","authors":"Mohammed Alghobiri","doi":"10.1007/s13278-023-01118-4","DOIUrl":"https://doi.org/10.1007/s13278-023-01118-4","url":null,"abstract":"","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136010543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Advancing aspect-based sentiment analysis with a novel architecture combining deep learning models CNN and bi-RNN with the machine learning model SVM","authors":"Sarsabene Hammi, Souha Mezghani Hammami, Lamia Hadrich Belguith","doi":"10.1007/s13278-023-01126-4","DOIUrl":"https://doi.org/10.1007/s13278-023-01126-4","url":null,"abstract":"","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136130138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Media production and consumption behaviors are changing in response to new technologies and demands, giving birth to a new generation of social applications. Among them, crowd journalism represents a novel way of constructing democratic and trustworthy news relying on ordinary citizens arriving at breaking news locations and capturing relevant videos using their smartphones. The ARTICONF project as reported by Prodan (Euro-Par 2019: parallel processing workshops, Springer, 2019) proposes a trustworthy, resilient, and globally sustainable toolset for developing decentralized applications (DApps) to address this need. Its goal is to overcome the privacy, trust, and autonomy-related concerns associated with proprietary social media platforms overflowed by fake news. Leveraging the ARTICONF tools, we introduce a new DApp for crowd journalism called MOGPlay. MOGPlay collects and manages audiovisual content generated by citizens and provides a secure blockchain platform that rewards all stakeholders involved in professional news production. Besides live streaming, MOGPlay offers a marketplace for audiovisual content trading among citizens and free journalists with an internal token ecosystem. We discuss the functionality and implementation of the MOGPlay DApp and illustrate four pilot crowd journalism live scenarios that validate the prototype.
{"title":"ARTICONF decentralized social media platform for democratic crowd journalism","authors":"Inês Rito Lima, Vasco Filipe, Claudia Marinho, Alexandre Ulisses, Antorweep Chakravorty, Atanas Hristov, Nishant Saurabh, Zhiming Zhao, Ruyue Xin, Radu Prodan","doi":"10.1007/s13278-023-01110-y","DOIUrl":"https://doi.org/10.1007/s13278-023-01110-y","url":null,"abstract":"Abstract Media production and consumption behaviors are changing in response to new technologies and demands, giving birth to a new generation of social applications. Among them, crowd journalism represents a novel way of constructing democratic and trustworthy news relying on ordinary citizens arriving at breaking news locations and capturing relevant videos using their smartphones. The ARTICONF project as reported by Prodan (Euro-Par 2019: parallel processing workshops, Springer, 2019) proposes a trustworthy, resilient, and globally sustainable toolset for developing decentralized applications (DApps) to address this need. Its goal is to overcome the privacy, trust, and autonomy-related concerns associated with proprietary social media platforms overflowed by fake news. Leveraging the ARTICONF tools, we introduce a new DApp for crowd journalism called MOGPlay. MOGPlay collects and manages audiovisual content generated by citizens and provides a secure blockchain platform that rewards all stakeholders involved in professional news production. Besides live streaming, MOGPlay offers a marketplace for audiovisual content trading among citizens and free journalists with an internal token ecosystem. We discuss the functionality and implementation of the MOGPlay DApp and illustrate four pilot crowd journalism live scenarios that validate the prototype.","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135394214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-14DOI: 10.1007/s13278-023-01127-3
Arnaldo Santoro, Alessandro Galeazzi, Teresa Scantamburlo, Andrea Baronchelli, Walter Quattrociocchi, Fabiana Zollo
Abstract The issue of vaccine hesitancy has posed a significant challenge during the Covid-19 pandemic, as it increases the risk of undermining public health interventions aimed at mitigating the spread of the virus. While the swift development of vaccines represents a remarkable scientific achievement, it has also contributed to skepticism and apprehension among some populations. Against this backdrop, the suspension of the AstraZeneca vaccine by the European Medicines Agency further exacerbated an already contentious debate around vaccine safety. This paper examines the Twitter discourse surrounding Covid-19 vaccines, focusing on the temporal and geographical dimensions of the discussion. Using over a year’s worth of data, we study the public debate in five countries (Germany, France, UK, Italy, and the USA), revealing differences in the interaction structure and in the production volume of questionable and reliable sources. Topic modeling highlights variations in the perspectives of reliable and questionable sources, but some similarities across nations. Also, we quantify the effect of vaccine announcement and suspension, finding that only the former had a significant impact in all countries. Finally, we analyze the evolution of the communities in the interaction network, revealing a relatively stable scenario with a few considerable shifts between communities with different levels of reliability. Our results suggest that major external events can be associated with changes in the online debate in terms of content production and interaction patterns. However, despite the AZ suspension, we do not observe any noticeable changes in the production and consumption of misinformation related to Covid-19 vaccines.
{"title":"Analyzing the changing landscape of the Covid-19 vaccine debate on Twitter","authors":"Arnaldo Santoro, Alessandro Galeazzi, Teresa Scantamburlo, Andrea Baronchelli, Walter Quattrociocchi, Fabiana Zollo","doi":"10.1007/s13278-023-01127-3","DOIUrl":"https://doi.org/10.1007/s13278-023-01127-3","url":null,"abstract":"Abstract The issue of vaccine hesitancy has posed a significant challenge during the Covid-19 pandemic, as it increases the risk of undermining public health interventions aimed at mitigating the spread of the virus. While the swift development of vaccines represents a remarkable scientific achievement, it has also contributed to skepticism and apprehension among some populations. Against this backdrop, the suspension of the AstraZeneca vaccine by the European Medicines Agency further exacerbated an already contentious debate around vaccine safety. This paper examines the Twitter discourse surrounding Covid-19 vaccines, focusing on the temporal and geographical dimensions of the discussion. Using over a year’s worth of data, we study the public debate in five countries (Germany, France, UK, Italy, and the USA), revealing differences in the interaction structure and in the production volume of questionable and reliable sources. Topic modeling highlights variations in the perspectives of reliable and questionable sources, but some similarities across nations. Also, we quantify the effect of vaccine announcement and suspension, finding that only the former had a significant impact in all countries. Finally, we analyze the evolution of the communities in the interaction network, revealing a relatively stable scenario with a few considerable shifts between communities with different levels of reliability. Our results suggest that major external events can be associated with changes in the online debate in terms of content production and interaction patterns. However, despite the AZ suspension, we do not observe any noticeable changes in the production and consumption of misinformation related to Covid-19 vaccines.","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134911652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-14DOI: 10.1007/s13278-023-01121-9
Nunziato Cassavia, Luca Caviglione, Massimo Guarascio, Angelica Liguori, Giuseppe Manco, Marco Zuppelli
Abstract An increasing volume of malicious software exploits information hiding techniques to cloak additional attack stages or bypass frameworks enforcing security. This trend has intensified with the growing diffusion of mobile ecosystems, and many threat actors now conceal scripts or configuration data within high-resolution icons. Even if machine learning has proven to be effective in detecting various hidden payloads, modern mobile scenarios pose further challenges in terms of scalability and privacy. In fact, applications can be retrieved from multiple stores or directly from the Web or social media. Therefore, this paper introduces an approach based on federated learning to reveal information hidden in high-resolution icons bundled with mobile applications. Specifically, multiple nodes are used to mitigate the impact of different privacy regulations, the lack of comprehensive datasets, or the computational burden arising from distributed stores and unofficial repositories. Results collected through simulations indicate that our approach achieves performances similar to those of centralized blueprints. Moreover, federated learning demonstrated its effectiveness in coping with simple “obfuscation” schemes like Base64 encoding and zip compression used by attackers to avoid detection.
{"title":"A federated approach for detecting data hidden in icons of mobile applications delivered via web and multiple stores","authors":"Nunziato Cassavia, Luca Caviglione, Massimo Guarascio, Angelica Liguori, Giuseppe Manco, Marco Zuppelli","doi":"10.1007/s13278-023-01121-9","DOIUrl":"https://doi.org/10.1007/s13278-023-01121-9","url":null,"abstract":"Abstract An increasing volume of malicious software exploits information hiding techniques to cloak additional attack stages or bypass frameworks enforcing security. This trend has intensified with the growing diffusion of mobile ecosystems, and many threat actors now conceal scripts or configuration data within high-resolution icons. Even if machine learning has proven to be effective in detecting various hidden payloads, modern mobile scenarios pose further challenges in terms of scalability and privacy. In fact, applications can be retrieved from multiple stores or directly from the Web or social media. Therefore, this paper introduces an approach based on federated learning to reveal information hidden in high-resolution icons bundled with mobile applications. Specifically, multiple nodes are used to mitigate the impact of different privacy regulations, the lack of comprehensive datasets, or the computational burden arising from distributed stores and unofficial repositories. Results collected through simulations indicate that our approach achieves performances similar to those of centralized blueprints. Moreover, federated learning demonstrated its effectiveness in coping with simple “obfuscation” schemes like Base64 encoding and zip compression used by attackers to avoid detection.","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134912644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-11DOI: 10.1007/s13278-023-01117-5
Kiran Fahd, Shah J. Miah
Abstract The academic intervention to predict at-risk higher education (HE) students requires effective data model development. Such data modelling projects in the HE context may have common issues related to (a) adopting small-scale modelling that gives limited options for early intervention and (b) using imbalanced data that hinders capturing effective details of poorly performing students. We address the issues going beyond the distribution-based algorithm, using a multilayer perceptron classifier which shows better on confusion metric, recall, and precision measures for identifying at-risk students. Our proposed deep learning-based model, which uses data augmentation techniques to supplement the data instances and balance the dataset, aims to improve the prediction accuracy of whether the student will fail or not based on their interaction with the learning management systems to prevent struggling students from evasion.
{"title":"Effectiveness of data augmentation to predict students at risk using deep learning algorithms","authors":"Kiran Fahd, Shah J. Miah","doi":"10.1007/s13278-023-01117-5","DOIUrl":"https://doi.org/10.1007/s13278-023-01117-5","url":null,"abstract":"Abstract The academic intervention to predict at-risk higher education (HE) students requires effective data model development. Such data modelling projects in the HE context may have common issues related to (a) adopting small-scale modelling that gives limited options for early intervention and (b) using imbalanced data that hinders capturing effective details of poorly performing students. We address the issues going beyond the distribution-based algorithm, using a multilayer perceptron classifier which shows better on confusion metric, recall, and precision measures for identifying at-risk students. Our proposed deep learning-based model, which uses data augmentation techniques to supplement the data instances and balance the dataset, aims to improve the prediction accuracy of whether the student will fail or not based on their interaction with the learning management systems to prevent struggling students from evasion.","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135981789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-04DOI: 10.1007/s13278-023-01115-7
Mohammadmahdi Zafarmand, Yashar Talebirad, Eric Austin, Christine Largeron, Osmar R Zaiane
{"title":"Fast local community discovery relying on the strength of links","authors":"Mohammadmahdi Zafarmand, Yashar Talebirad, Eric Austin, Christine Largeron, Osmar R Zaiane","doi":"10.1007/s13278-023-01115-7","DOIUrl":"https://doi.org/10.1007/s13278-023-01115-7","url":null,"abstract":"","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":" ","pages":"1-21"},"PeriodicalIF":2.8,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49592107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-02DOI: 10.1007/s13278-023-01116-6
J. A. Núñez-Mora, Román A. Mendoza-Urdiales
{"title":"Social sentiment and impact in US equity market: an automated approach","authors":"J. A. Núñez-Mora, Román A. Mendoza-Urdiales","doi":"10.1007/s13278-023-01116-6","DOIUrl":"https://doi.org/10.1007/s13278-023-01116-6","url":null,"abstract":"","PeriodicalId":21842,"journal":{"name":"Social Network Analysis and Mining","volume":" ","pages":"1-11"},"PeriodicalIF":2.8,"publicationDate":"2023-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46997532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：