The 2022 Workshop on Reducing Online Misinformation through Credible Information Retrieval (ROMCIR 2022), at its Second Edition as part of the Satellite Events of the 44th European Conference on Information Retrieval (ECIR 2022), is concerned with providing users with access to genuine information, to mitigate the information disorder phenomenon characterizing the current online environment. This problem is very broad, as it concerns diferent information objects (e.g., Web pages, online accounts, social media posts, etc.) on diferent platforms, and diferent domains and purposes (e.g., detecting fake news, retrieving genuine healthrelated information, reducing propaganda and hate-speech, etc.). In this context, all those approaches that can serve, from diferent perspectives, to tackle the genuine information access problem, find their place. In particular, this year articles have been submitted that addressed the problem of preventing access to health misinformation and assessing the genuineness of multi-modal information.
Coming into contact with diferent types of misleading content that is propagated online, especially
through social media platforms [
This scenario is due to the so-called information disorder phenomenon [12], which indicates the proliferation of diferent forms of (online) communication pollution, encompassing dis-, mis-, and malinformation. Specifically, misinformation is the spread of false content resulting from the spreader’s ignorance; disinformation is a form of intentional sharing of false content to produce harm; malinformation indicates the spread of (private) information that is based on reality, having the same harmful intent (e.g., the despicable act of revenge porn).
Access to this non-genuine information is made easier and easier due to the fact that, from a technological point of view, information is produced at a speed and volume never seen before, almost without any trusted traditional intermediary [13, 14]. Faced with this huge amount of information, and the uncertainty associated with its degree of genuineness, human cognitive abilities are not always suficient to take well-informed decisions [15].
In this context, it is clear that the problem of guaranteeing access to genuine information online needs to find efective solutions, despite (and precisely because of) it is very broad, as it concerns different information objects (e.g., Web pages, online accounts, social media posts, etc.), diferent online platforms (e.g., Web portals, social networking services, question-answering systems, etc.), and diferent domains and purposes (e.g., detecting fake news, retrieving genuine health-related information, reducing propaganda and hate-speech, etc.).
Within the ECIR conference, the key goal of the Workshop is to encourage a discussion between researchers, also belonging to diferent disciplines, and propose innovative approaches, about the problem of guarantee to users access to genuine information that does not distort their perception of reality, through Information Retrieval solutions [16]. In recent years, despite numerous approaches have been proposed to tackle the considered issue in diferent contexts, and for diferent purposes, we are still a long way from having found completely efective and domain-independent solutions.
The problem is still of great interest with respect to many research directions, such as the access to and retrieval of genuine information, the early detection of dis-/mis-/mal-information, the development of solutions that can be understood by final users (explainable AI), the study of the problem in the health domain, the study of the relationship between security, privacy and genuineness in information access and dissemination, the consideration of multi-modal information in assessing genuineness.
In this scenario, the role of researchers working in the fields of Information Retrieval, Social Computing, Social Sciences, Data and Web Science and other related research areas, is crucial to investigate the above-mentioned research directions.
All those approaches that can serve, from diferent perspectives, to tackle the genuine information access problem, find their place in ROMCIR 2022. Specifically, the topics of interest include, but are not limited to: • Access to/retrieval of genuine information • Bias detection • Bot/spam/troll detection • Computational fact-checking • Crowdsourcing for information genuineness assessment • Deep fakes and multi-modal misinformation detection • Dis/misinformation detection • Evaluation strategies in assessing dis/misinformation • Fake news/reviews detection • Filter bubble/echo chamber/polarization detection • Harassment/bullying/hate-speech/propaganda detection • Security, privacy and information genuineness • Sentiment/emotional analysis and stance detection • Trust and reputation systems • Understanding and guiding the societal reaction in the presence of dis/misinformation
Both theoretical studies, model-driven, and data-driven approaches, supported by publicly available datasets, are more than welcome.
The ROMCIR 2022 Workshop received 10 submissions, of which 6 were accepted, so with an acceptance rate of 60%. Articles have been submitted from four diferent countries, i.e., Germany, India, UK, and USA. The accepted articles, collected in these Proceedings, have primarily considered two issues from distinct points of view. The first issue concerns access to genuine information in the health-related domain; the second issue concerns access to multi-modal genuine information.
With respect to the first issue, in the article by Fröbe et al. entitled: “Using Keyqueries to Reduce Misinformation in Health-Related Search Results”, the authors investigate whether explicit relevance feedback provided by experts can guide query expansion methods to formulate queries that return fewer misleading or wrong results. In contrast to standard query expansion methods that pay no attention to feedback document ranks in expanded query results, the authors experiment with a keyquery-based approach to identify expanded queries for which feedback documents are ranked as high as possible. In the article by Huang et al. entitled: “Fight Against COVID-19 Misinformation via Clustering-Based Subset Selection Fusion Methods”, the authors try to improve the retrieval quality of search engines w.r.t. diferent relevance dimensions via a data fusion technique. In particular, a clustering-based approach is proposed for selecting a subset of IR systems from all the available ones, for finding the most relevant, credible, and correct documents talking about COVID-19. Still in the health domain, the article by Pankovska et al., entitled: “Suspicious Sentence Detection and Claim Verification in the COVID-19 Domain”, addresses the claim verification and fact-check-worthiness issues, by proposing an approach that involves a two-step claim verification procedure consisting of a fake news detection task in the form of binary sequence classification and fact-checking using the Google Fact Check Tools. The aim of the authors is to alert the reader that a document contains suspicious statements, even if no already validated similar claims exist. The last article that deals with health misinformation, this time from a more high-level perspective, is the one by Janzen et al. entitled “Cognitive security and resilience: A social-ecological model of disinformation and other harms with applications to COVID-19 vaccine information behaviors”. In this paper, the authors propose a novel application of Brofenbrenner’s social ecological model to the study of cognitive security and resilience in the context of information disorder. First, they describe the refitting of the model from public health and human development to cognitive security. Using existing literature in the field, they identify the key factors at each level of influence that shape susceptibility and resilience to information disorder. They also consider the dynamic interactions between individuals, groups, societies, and characteristics of the technological environment, including how algorithms interact with individual behaviors, policies, and organizational decision-making to shape access to and discoverability of genuine information. Finally, they describe an application of the model to a use case involving COVID-19-related information behaviors.
Coming to the second problem addressed by the articles submitted to ROMCIR 2022, namely that of multi-modal genuine information access, the article by Aghada entitled: “An Alternative Approach to Ranking Videos and Measuring Dissimilarity Between Video Content and Titles”, proposes a statistical approach to video retrieval and ranking by introducing a novel dissimilarity measure acting on a video’s audio-visual content and its title, hence aiding in video click-bait detection. Finally, in the paper by Kirdemir et al. entitled: “Towards Detecting Coordinated Inauthentic Behaviors on YouTube”, the authors aim to explore new approaches to assess latent and implicit characteristics of coordination among users in YouTube channels that can indicate manipulation of information and communication. In particular, they propose computational models leveraging multi-step time-series analysis of engagement trends, network structural feature-based analysis, and a combination of unsupervised and supervised machine learning techniques.
As part of the Workshop, a Keynote Speech entitled “Fake News Detection: Limited Ground Truth, Limited Text, No Understanding of Spreading Intent” was given by Reza Zafarani, on current open issues that still concern fake news detection.
Abstract: “Fake news” is now viewed as one of the greatest threats to democracies and journalism. The massive spread of fake news has weakened public trust in governments and its potential impact on various political outcomes such as the Brexit is yet to be realized. We will briefly review fake news detection techniques, along with some of the current challenges that these methods face. We will discuss some recent advancements to tackle these challenges, particularly focusing on multi-modal fake news analysis and assessing the intent of fake news spreaders.
Computer Science at Syracuse University. His research interests are in Data Mining, Machine Learning, Social Media Mining, and Social Network Analysis. His research has been published in major academic venues and highlighted in various scientific and news outlets. He is the principal author of “Social Media Mining: An Introduction” a textbook by Cambridge University Press and the associate editor for SIGKDD Explorations and Frontiers in communication. He is the winner of the NSF CAREER award, President’s Award for Innovation, and outstanding teaching award at Arizona State University. Web site: http://reza.zafarani.net/
The ROMCIR 2022 Organizing Team was composed of the following people with respect to their distinct roles.
ics and Telematics, part of the National Research Council (IIT-CNR), Pisa, Italy, under the Trust, Security and Privacy research unit. She collaborates with the Sysma unit at IMT School for Advanced Studies, in Lucca, Italy. Her field of research lies between Cybersecurity and Data Science. She studies novel techniques for online fake news/fake accounts detection. She is in the core team of the TOols for Fighting FakEs (TOFFEe) project, funded by IMT, and WP leader in H2020 Medina, where she studies how to automatically translate NL cloud security requirements to machinereadable, enforceable policies. Web site: https://www.iit.cnr.it/en/marinella.petrocchi/
Bicocca, Department of Informatics, Systems, and Communication (DISCo), Milan, Italy. He works in the Information and Knowledge Representation, Retrieval and Reasoning (IKR3) Lab. He is involved in numerous research initiatives that involve accessing and retrieving information, especially genuine information. He has been Co-chair of several Special Tracks and Workshops at International Conferences, General Cochair of MDAI 2019, and Co-organizer of the First Edition of the ROMCIR
Workshop. He is Associate Editor of Social Network Analysis and Mining (SNAM), Springer-Verlag, and Editorial Board Member of Online Social Networks and Media (OSNEM), Elsevier. His main research activities include Social Computing, Information Retrieval, Natural Language Processing, Text Mining, and User Modeling. On these topics, he has published more than 80 research works in International Journals, at International Conferences, as Monographs, and Book Chapters. Web site: https://ikr3.disco.unimib.it/people/marco-viviani/
Rishabh Upadhyay, PhD Student. University of Milano-Bicocca, Department of Informatics, Systems, and Communication (DISCo), Milan, Italy.
Web site: https://ikr3.disco.unimib.it/people/rishabh-upadhyay/ 6.3. Program Committee • Rino Falcone, Inst. of Cognitive Sciences and Technologies (ISTC) – CNR, Rome, Italy • Carlos A. Iglesias, Universidad Politécnica de Madrid, Madrid, Spain • Petr Knoth, The Open University, London, UK • Udo Kruschwitz, University of Regensburg, Regensburg, Germany • Preslav Nakov, Qatar Computing Research Institute, HBKU, Doha, Qatar • Symeon Papadopoulos, Inf. Tech. Inst. (ITI), Thessaloniki, Greece • Marinella Petrocchi, Inst. of Informatics and Telematics (IIT) – CNR, Pisa, Italy • Francesco Pierri, Politecnico di Milano, Milan, Italy • Adrian Popescu, CEA LIST, Gif-sur-Yvette, France • Paolo Rosso, Universitat Politècnica de València, València, Spain • Fabio Saracco, Centro Ricerche Enrico Fermi (CREF), Florence, Italy • Marco Viviani, University of Milano-Bicocca, Milan, Italy • Xinyi Zhou, Syracuse University, Syracuse, NY, USA • Arkaitz Zubiaga, Queen Mary University of London, London, UK
We would like to thank the authors of the submitted articles for their interest in the considered problem, the Keynote Speaker for the interest aroused in new research directions, and the members of the Program Committee for their valuable contribution to the success of the ROMCIR 2022 Workshop.
More information about the 2022 Edition of the ROMCIR Workshop can be found at the following URL: https://romcir2022.disco.unimib.it/ [9] S. Di Sotto, M. Viviani, Health misinformation detection in the social web: An overview and a data science approach, International Journal of Environmental Research and Public Health 19 (2022) 2173. [10] G. Caldarelli, R. De Nicola, M. Petrocchi, M. Pratelli, F. Saracco, Flow of online misinformation during the peak of the COVID-19 pandemic in italy, EPJ Data Sci. 10 (2021) 34. doi:10.1140/ epjds/s13688-021-00289-4. [11] V. E. Valenti, A. P. d. Silva, The efect of negationism on public health, Journal of Human Growth and Development 31 (2021) 189–191. [12] C. Wardle, H. Derakhshan, Information disorder: Toward an interdisciplinary framework for research and policy making, Council of Europe Report 27 (2017). [13] B. Carminati, E. Ferrari, M. Viviani, Security and trust in online social networks, Synthesis
Lectures on Information Security, Privacy, & Trust 4 (2013) 1–120. [14] G. Eysenbach, Credibility of health information and digital media: New perspectives and implications for youth, in: M. M. Metzger, A. J. Flanagin (Eds.), Digital Media, Youth, and Credibility, The MIT Press, 2008, pp. 123–154. [15] M. J. Metzger, A. J. Flanagin, Credibility and trust of information in online environments: The use of cognitive heuristics, Journal of pragmatics 59 (2013) 210–220. [16] A. L. Ginsca, A. Popescu, M. Lupu, Credibility in information retrieval, Foundations and Trends in Information Retrieval 9 (2015) 355–475.