Pub Date : 2020-11-09DOI: 10.1109/ISI49825.2020.9280525
Jefferson Viana Fonseca Abreu, C. Ralha, J. Gondim
Online social networks provide a novel channel to allow interaction between human beings. Its success has attracted interest in attacking and exploiting them through a wide range of unethical activities, such as malicious actions to manipulate users. One of the methods to carry out these abuses is the use of bots on Twitter. Recent examples of bots influencing public opinion in the election process demonstrate their potential harm to the democratic world. Such malicious behavior needs to be checked and its effects should be diminished. Recently, machine learning (ML) classifiers to distinguish between real and bot accounts have proven advances. Thus, in this work four ML algorithms were tested using a public dataset and a few expressive features based on simple user profile counters for the classification of bots on Twitter. We measured their performance compared to one state–of–the–art bot detection work. The classifier accuracy was considered homogeneous with a mean of 0.8549 and 0.1889 of standard deviation. Besides, all multiclass classifiers obtained AUCs greater than 0.9 indicating a practical benefit for bot detection on Twitter.
{"title":"Twitter Bot Detection with Reduced Feature Set","authors":"Jefferson Viana Fonseca Abreu, C. Ralha, J. Gondim","doi":"10.1109/ISI49825.2020.9280525","DOIUrl":"https://doi.org/10.1109/ISI49825.2020.9280525","url":null,"abstract":"Online social networks provide a novel channel to allow interaction between human beings. Its success has attracted interest in attacking and exploiting them through a wide range of unethical activities, such as malicious actions to manipulate users. One of the methods to carry out these abuses is the use of bots on Twitter. Recent examples of bots influencing public opinion in the election process demonstrate their potential harm to the democratic world. Such malicious behavior needs to be checked and its effects should be diminished. Recently, machine learning (ML) classifiers to distinguish between real and bot accounts have proven advances. Thus, in this work four ML algorithms were tested using a public dataset and a few expressive features based on simple user profile counters for the classification of bots on Twitter. We measured their performance compared to one state–of–the–art bot detection work. The classifier accuracy was considered homogeneous with a mean of 0.8549 and 0.1889 of standard deviation. Besides, all multiclass classifiers obtained AUCs greater than 0.9 indicating a practical benefit for bot detection on Twitter.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"8 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83660827","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 : 2019-01-01DOI: 10.1109/ISI.2019.8823359
Wenzheng Li, Yijun Gu, An Wang, Kunming Li
{"title":"Improvement of Ego Network Detection Algorithm Based on Cluster Validity Index","authors":"Wenzheng Li, Yijun Gu, An Wang, Kunming Li","doi":"10.1109/ISI.2019.8823359","DOIUrl":"https://doi.org/10.1109/ISI.2019.8823359","url":null,"abstract":"","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"104 1","pages":"35-40"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79192153","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}
While much is known about how Twitter is used for specific tasks or by particular groups of users, we understand surprisingly little about how the service is used generally on a daily basis. To learn more about general Twitter behaviour we perform a cluster analysis on a rich set of longitudinal interaction log data describing interactions 44 users had with the Twitter website over a 5 month period. We report on and interpret 5 clusters representing common usage patterns with the service.
{"title":"Using Sessions from Clickstream Data Analysis to Uncover Different Types of Twitter Behaviour","authors":"F. Meier, Johannes Aigner, David Elsweiler","doi":"10.18452/1452","DOIUrl":"https://doi.org/10.18452/1452","url":null,"abstract":"While much is known about how Twitter is used for specific tasks or by particular groups of users, we understand surprisingly little about how the service is used generally on a daily basis. To learn more about general Twitter behaviour we perform a cluster analysis on a rich set of longitudinal interaction log data describing interactions 44 users had with the Twitter website over a 5 month period. We report on and interpret 5 clusters representing common usage patterns with the service.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"14 1","pages":"237-250"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77498469","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}
Christoph Schindler, Julian Hocker, Lars Müller, M. Maleshkova, T. Weller
Recently, practice theory has been established alongside humanities and social sciences in historical research and has aligned analysis according to materializations of loosely interlinked arrangements of practices, materialities, and actors (cf. Reh, 2014). While digital humanities have proven its great capacity to deal with massive data (distant reading), the digital enhancement of qualitative approaches is lacking (cf. Drucker, 2012). This desideratum is addressed in this project which uses a semantic graph to create a linked web and offering tools for combining qualitative and quantitative analysis.
{"title":"Grasping the Materializations of Practices in Digital Humanities - A Semantic Research Environment for Analyzing Exam Grading Practices in German High Schools","authors":"Christoph Schindler, Julian Hocker, Lars Müller, M. Maleshkova, T. Weller","doi":"10.18452/1470","DOIUrl":"https://doi.org/10.18452/1470","url":null,"abstract":"Recently, practice theory has been established alongside humanities and social sciences in historical research and has aligned analysis according to materializations of loosely interlinked arrangements of practices, materialities, and actors (cf. Reh, 2014). While digital humanities have proven its great capacity to deal with massive data (distant reading), the digital enhancement of qualitative approaches is lacking (cf. Drucker, 2012). This desideratum is addressed in this project which uses a semantic graph to create a linked web and offering tools for combining qualitative and quantitative analysis.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"60 1","pages":"365-367"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84466380","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}
In most universities in Europe, the barriers to enter into a LIS master degree after earning a degree in another subject are typically high. The same is true for the international mobility of students enrolled in BA or MA LIS programs in Europe. The EINFOSE project (Information Science Education: Encouraging mobility and learning outcomes harmonization) aims at lowering this barriers by offering summer schools on core topics of information science and by providing open educational resources (OER) on these topics in the long term.
{"title":"Lowering the Barriers to Entry into LIS Master Programs - The EINFOSE Project","authors":"Thomas Mandl, Tatjana Aparac-Jelusic","doi":"10.18452/1466","DOIUrl":"https://doi.org/10.18452/1466","url":null,"abstract":"In most universities in Europe, the barriers to enter into a LIS master degree after earning a degree in another subject are typically high. The same is true for the international mobility of students enrolled in BA or MA LIS programs in Europe. The EINFOSE project (Information Science Education: Encouraging mobility and learning outcomes harmonization) aims at lowering this barriers by offering summer schools on core topics of information science and by providing open educational resources (OER) on these topics in the long term.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"23 1","pages":"377-379"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83247651","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}
K. Jeffery, C. Meghini, C. Concordia, T. Patkos, Valérie Brasse, Jacco van Ossenbruck, Yannis Marketakis, N. Minadakis, E. Marchetti
This paper describes the Reference Architecture of the enhanced VRE (e-VRE), a Virtual Research Environment defined in the context of the VRE4EIC Project, funded by EU H2020 e-Infrastructure program. e-VRE is designed to overcome limits of existing VREs with respect to a number of orthogonal dimensions: improving the quality of VRE user experience by providing user centered, secure, privacy compliant, sustainable environments for accessing data, composing workflows and tracking data publications; increasing VRE usage in multidisciplinary research domains by abstracting and reusing building blocks and workflows from existing VRE initiatives; improving the interoperability of heterogeneous discovery, contextual and detailed metadata across all layers of the VRE.
{"title":"A Reference Architecture for Virtual Research Environments","authors":"K. Jeffery, C. Meghini, C. Concordia, T. Patkos, Valérie Brasse, Jacco van Ossenbruck, Yannis Marketakis, N. Minadakis, E. Marchetti","doi":"10.18452/1448","DOIUrl":"https://doi.org/10.18452/1448","url":null,"abstract":"This paper describes the Reference Architecture of the enhanced VRE (e-VRE), a Virtual Research Environment defined in the context of the VRE4EIC Project, funded by EU H2020 e-Infrastructure program. e-VRE is designed to overcome limits of existing VREs with respect to a number of orthogonal dimensions: improving the quality of VRE user experience by providing user centered, secure, privacy compliant, sustainable environments for accessing data, composing workflows and tracking data publications; increasing VRE usage in multidisciplinary research domains by abstracting and reusing building blocks and workflows from existing VRE initiatives; improving the interoperability of heterogeneous discovery, contextual and detailed metadata across all layers of the VRE.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"87 1","pages":"76-88"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84382680","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}
J. Beel, S. Dinesh, Philipp Mayr, Zeljko Carevic, Raghvendra Jain
Stereotype and most-popular recommendations are widely neglected in the research-paper recommender-system and digital-library community. In other domains such as movie recommendations and hotel search, however, these recommendation approaches have proven their effectiveness. We were interested to find out how stereotype and most-popular recommendations would perform in the scenario of a digital library. Therefore, we implemented the two approaches in the recommender system of GESIS’ digital library Sowiport, in cooperation with the recommendations-as-a-service provider Mr. DLib. We measured the effectiveness of most-popular and stereotype recommendations with click-through rate (CTR) based on 28 million delivered recommendations. Most-popular recommendations achieved a CTR of 0.11%, and stereotype recommendations achieved a CTR of 0.124%. Compared to a “random recommendations” baseline (CTR 0.12%), and a contentbased filtering baseline (CTR 0.145%), the results are discouraging. However, for reasons explained in the paper, we concluded that more research is In: M. Gäde/V. Trkulja/V. Petras (Eds.): Everything Changes, Everything Stays the Same? Understanding Information Spaces. Proceedings of the 15 International Symposium of Information Science (ISI 2017), Berlin, 13—15 March 2017. Glückstadt: Verlag Werner Hülsbusch, pp. 96—108. Stereotype and Most-Popular Recommendations ... 97 necessary about the effectiveness of stereotype and most-popular recommendations in digital libraries.
在研究论文推荐系统和数字图书馆社区中，刻板印象和最受欢迎的推荐被广泛忽视。然而，在电影推荐和酒店搜索等其他领域，这些推荐方法已经证明了它们的有效性。我们很想知道在数字图书馆的场景中，刻板印象和最受欢迎的推荐是如何执行的。因此，我们与推荐即服务提供商DLib先生合作，在GESIS的数字图书馆Sowiport的推荐系统中实施了这两种方法。我们基于2800万条推荐，用点击率(CTR)来衡量最受欢迎推荐和刻板印象推荐的有效性。最流行推荐的点击率为0.11%，刻板印象推荐的点击率为0.124%。与“随机推荐”基线(CTR 0.12%)和基于内容的过滤基线(CTR 0.145%)相比，结果令人沮丧。然而，由于论文中解释的原因，我们得出的结论是，更多的研究是in: M. Gäde/V。Trkulja / V。彼得拉斯(编辑):一切都在变化，一切都保持不变?理解信息空间。第15届国际信息科学研讨会论文集(ISI 2017)，柏林，2017年3月13-15日。glickstadt: Verlag Werner h lsbusch，第96-108页。刻板印象和最受欢迎的建议……关于数字图书馆中刻板印象和最受欢迎的推荐的有效性的必要性。
{"title":"Stereotype and Most-Popular Recommendations in the Digital Library Sowiport","authors":"J. Beel, S. Dinesh, Philipp Mayr, Zeljko Carevic, Raghvendra Jain","doi":"10.18452/1441","DOIUrl":"https://doi.org/10.18452/1441","url":null,"abstract":"Stereotype and most-popular recommendations are widely neglected in the research-paper recommender-system and digital-library community. In other domains such as movie recommendations and hotel search, however, these recommendation approaches have proven their effectiveness. We were interested to find out how stereotype and most-popular recommendations would perform in the scenario of a digital library. Therefore, we implemented the two approaches in the recommender system of GESIS’ digital library Sowiport, in cooperation with the recommendations-as-a-service provider Mr. DLib. We measured the effectiveness of most-popular and stereotype recommendations with click-through rate (CTR) based on 28 million delivered recommendations. Most-popular recommendations achieved a CTR of 0.11%, and stereotype recommendations achieved a CTR of 0.124%. Compared to a “random recommendations” baseline (CTR 0.12%), and a contentbased filtering baseline (CTR 0.145%), the results are discouraging. However, for reasons explained in the paper, we concluded that more research is In: M. Gäde/V. Trkulja/V. Petras (Eds.): Everything Changes, Everything Stays the Same? Understanding Information Spaces. Proceedings of the 15 International Symposium of Information Science (ISI 2017), Berlin, 13—15 March 2017. Glückstadt: Verlag Werner Hülsbusch, pp. 96—108. Stereotype and Most-Popular Recommendations ... 97 necessary about the effectiveness of stereotype and most-popular recommendations in digital libraries.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"1 1","pages":"96-108"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79594033","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}
D. Lewandowski, Sebastian Sünkler, Friederike Kerkmann
In an online experiment using a representative sample of the German online population (n = 1,000), we compare users’ selection behaviour on two versions of the same Google search engine results page (SERP), one showing advertisements and organic results, the other showing organic results only. Selection behaviour is analyzed in relation to users’ knowledge on Google’s business model, on SERP design, and on these users’ actual performance in marking advertisements on SERPs correctly. We find that users who were not able to mark ads correctly selected ads significantly more often. This leads to the conclusion that ads need to be labeled more clearly, and that there is a need for more information literacy in search engine users.
{"title":"Are Ads on Google Search Engine Results Pages Labeled Clearly Enough? - The Influence of Knowledge on Search Ads on Users' Selection Behaviour","authors":"D. Lewandowski, Sebastian Sünkler, Friederike Kerkmann","doi":"10.18452/1450","DOIUrl":"https://doi.org/10.18452/1450","url":null,"abstract":"In an online experiment using a representative sample of the German online population (n = 1,000), we compare users’ selection behaviour on two versions of the same Google search engine results page (SERP), one showing advertisements and organic results, the other showing organic results only. Selection behaviour is analyzed in relation to users’ knowledge on Google’s business model, on SERP design, and on these users’ actual performance in marking advertisements on SERPs correctly. We find that users who were not able to mark ads correctly selected ads significantly more often. This leads to the conclusion that ads need to be labeled more clearly, and that there is a need for more information literacy in search engine users.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"2015 1","pages":"62-74"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88964831","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}
Felix Hamborg, Norman Meuschke, Corinna Breitinger, Bela Gipp
Depending on the news source, a reader can be exposed to a different narrative and conflicting perceptions for the same event. Today, news aggregators help users cope with the large volume of news published daily. However, aggregators focus on presenting shared information, but do not expose the different perspectives from articles on same topics. Thus, users of such aggregators suffer from media bias, which is often implemented intentionally to influence public opinion. In this paper, we present NewsBird, an aggregator that presents shared and different information on topics. Currently, NewsBird reveals different perspectives on international news. Our system has led to insights about media bias and news analysis, which we use to propose approaches to be investigated in future research. Our vision is to provide a system that reveals media bias, and thus ultimately allows users to make their own judgement on the potential bias inherent in news.
{"title":"Identification and Analysis of Media Bias in News Articles - The Impact of Objectivity and Believability on Corporate Decision Making and Performance","authors":"Felix Hamborg, Norman Meuschke, Corinna Breitinger, Bela Gipp","doi":"10.18452/1446","DOIUrl":"https://doi.org/10.18452/1446","url":null,"abstract":"Depending on the news source, a reader can be exposed to a different narrative and conflicting perceptions for the same event. Today, news aggregators help users cope with the large volume of news published daily. However, aggregators focus on presenting shared information, but do not expose the different perspectives from articles on same topics. Thus, users of such aggregators suffer from media bias, which is often implemented intentionally to influence public opinion. In this paper, we present NewsBird, an aggregator that presents shared and different information on topics. Currently, NewsBird reveals different perspectives on international news. Our system has led to insights about media bias and news analysis, which we use to propose approaches to be investigated in future research. Our vision is to provide a system that reveals media bias, and thus ultimately allows users to make their own judgement on the potential bias inherent in news.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"140 1","pages":"224-236"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73287515","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}
In this paper we present an empirical study comparing user studies and expert evaluations based on a specific set of heuristics for evaluating information appliances with a heuristic walkthrough. The study looks at an e-book reader as well as a digital music player. In the user study, question-answer protocols are used as means of intervention during the experiments. To gain insight into performance of the evaluation methods the identified problem sets were analyzed. Results for the thoroughness, validity and effectiveness are presented and compared with prior studies.
{"title":"Comparing Heuristic Walkthrough and User Studies in Evaluating Digital Appliances","authors":"Eva-Maria Meier, Patricia Böhm, Christian Wolff","doi":"10.18452/1453","DOIUrl":"https://doi.org/10.18452/1453","url":null,"abstract":"In this paper we present an empirical study comparing user studies and expert evaluations based on a specific set of heuristics for evaluating information appliances with a heuristic walkthrough. The study looks at an e-book reader as well as a digital music player. In the user study, question-answer protocols are used as means of intervention during the experiments. To gain insight into performance of the evaluation methods the identified problem sets were analyzed. Results for the thoroughness, validity and effectiveness are presented and compared with prior studies.","PeriodicalId":90875,"journal":{"name":"ISI ... : ... IEEE Intelligence and Security Informatics. IEEE International Conference on Intelligence and Security Informatics","volume":"35 1","pages":"146-157"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77390103","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：