Veracity assessment of online dataShow others and affiliations
2020 (English)In: Decision Support Systems, ISSN 0167-9236, E-ISSN 1873-5797, Vol. 129, article id 113132Article in journal (Refereed) Published
Abstract [en]
Fake news, malicious rumors, fabricated reviews, generated images and videos, are today spread at an unprecedented rate, making the task of manually assessing data veracity for decision-making purposes a daunting task. Hence, it is urgent to explore possibilities to perform automatic veracity assessment. In this work we review the literature in search for methods and techniques representing state of the art with regard to computerized veracity assessment. We study what others have done within the area of veracity assessment, especially targeted towards social media and open source data, to understand research trends and determine needs for future research. The most common veracity assessment method among the studied set of papers is to perform text analysis using supervised learning. Regarding methods for machine learning much has happened in the last couple of years related to the advancements made in deep learning. However, very few papers make use of these advancements. Also, the papers in general tend to have a narrow scope, as they focus on solving a small task with only one type of data from one main source. The overall veracity assessment problem is complex, requiring a combination of data sources, data types, indicators, and methods. Only a few papers take on such a broad scope, thus, demonstrating the relative immaturity of the veracity assessment domain. © 2019 The Authors
Place, publisher, year, edition, pages
Elsevier B.V. , 2020. Vol. 129, article id 113132
Keywords [en]
Credibility, Data quality, Fake news, Online data, Social media, Veracity assessment, Decision making, Machine learning, Paper, Social networking (online), Deep learning
National Category
Natural Sciences
Identifiers
URN: urn:nbn:se:ri:diva-43403DOI: 10.1016/j.dss.2019.113132Scopus ID: 2-s2.0-85076227196OAI: oai:DiVA.org:ri-43403DiVA, id: diva2:1390339
Note
Funding details: Horizon 2020 Framework Programme, H2020, 832921; Funding details: Försvarsmakten; Funding details: Research and Development; Funding text 1: We gratefully acknowledge the help obtained from the librarian Alexis Wiklund, for performing the initial database literature searches. This work was supported by the Swedish Armed Forces’ research and development program and the European Union Horizon 2020 program (grant agreement no. 832921 ). Appendix A; Funding text 2: Supplementary data to this article can be found online at https://doi.org/10.1016/j.dss.2019.113132 . The supplementary data contains the full list of reviewed papers for this study. Marianela García Lozano is a senior scientist at the Swedish Defence Research Agency (FOI) since 2001. Her research interests include information and knowledge modeling, veracity assessment, software development in distributed systems, web mining, machine learning, and natural language processing. Marianela received her M.Sc. degree in Computer Science and Engineering in 2003 and her Licentiate degree in Electronic and Computer Systems in 2010 from the Royal Institute of Technology (KTH). Marianela’s licentiate thesis is on the topic of distributed systems. Joel Brynielsson is a research director at the Swedish Defence Research Agency (FOI) and an associate professor at the Royal Institute of Technology (KTH). He previously worked as an assistant professor at the Swedish Defence University. Joel is Docent (Habilitation) in Computer Science (2015), and holds a Ph.D. in Computer Science (2006) and an M.Sc. in Computer Science and Engineering (2000) from KTH. His research interests include uncertainty management, information fusion, probabilistic expert systems, the theory and practice of decision-making, command and control, operations research, game theory, web mining, privacy-preserving data mining, cyber security, and computer security education. He is the author or co-author of more than 150 papers and reports devoted to these subjects. Ulrik Franke is a senior researcher at Research Institutes of Sweden (RISE). Prior to joining RISE, he was a senior scientist at the Swedish Defence Research Agency (FOI). His research interests include IT service availability, enterprise architecture, cyber insurance, and cyber situational awareness. He received his M.Sc. and Ph.D. degrees in 2007 and 2012, respectively, both from the Royal Institute of Technology (KTH) in Stockholm, Sweden. Magnus Rosell is a scientist at the Swedish Defence Research Agency (FOI), where he manages a long-term research project on semi-automatic intelligence analysis. He previously worked at Recorded Future, a web intelligence company, where he designed and implemented essential parts of the core engine for extracting events from free text. Magnus holds a Ph.D. in Computer Science (2009) and an M.Sc. in Engineering Physics (2002) from the Royal Institute of Technology (KTH). His research interests include natural language processing, machine learning, data and web mining, decision support, and crisis management. Edward Tjörnhammar is a Ph.D. candidate at the Royal Institute of Technology (KTH) since 2015 and a research engineer at the Swedish Defence Research Agency (FOI) since 2006. His interests include distributed systems, data mining, and machine learning. Edward received his M.Sc. degree in Computer Science and Engineering in 2012 from the Royal Institute of Technology. Edward's master's thesis is on the topic of distributed systems. Stefan Varga Swedish Armed Forces, is a professional Ph.D. student (Computer Science) at the Royal Institute of Technology. Major (air force) Varga has worked in the military specialty fields of air surveillance, communications, and intelligence. He is an armed forces military specialist in command and control systems development. Stefan is a graduate from the Advanced Management Program at the Information Resources Management College of the U.S. National Defense University. He is a NATO cyber security professional trained by the U.S. Naval Post Graduate School and the NATO School Oberammergau, Germany. His research interests include cyber security, cyber situational awareness, and decision support. Vladimir Vlassov is a professor in Computer Systems at the Royal Institute of Technology (KTH) in Stockholm, Sweden. Prior to coming to KTH in 1993, he was an assistant and associate professor at the Electrotechnical University LETI of Saint Petersburg, Russia (19851993). He was a visiting scientist at MIT (1998), and a researcher at the University of Massachusetts Amherst (2004). Vladimir has co-authored more than 150 research papers. His research interests include big data analytics, data-intensive computing, autonomic computing, and distributed and parallel computing.
2020-01-312020-01-312024-07-04Bibliographically approved