EUNOMIA at SOCINFO2020: Challenging Misinformation; Exploring Limits and Approaches

December 22nd, 2020 by

EUNOMIA project joined forces with H2020 project Co-Inform delivering together the workshop “Challenging Misinformation: Exploring Limits and Approaches” at the Social Informatics Conference 2020 (SocInfo2020) on 6th October 2020.

Pinelopi Troullinou (Trilateral Research) and Diotima Bertel (SYNYO) from EUNOMIA project invited researchers and practitioners to reflect on the existing approaches and the limitations of current socio-technical solutions to tackle misinformation. The objective of the workshop was to bring together stakeholders from diverse backgrounds to develop collaborations and synergies towards the common goal of social media users’ empowerment.

Four papers were presented at the workshop; Gautam Kishore Shahi from the University of Duisburg-Essen in Germany discussed the different conspiracy theories related to COVID-19 spread in the web and the challenges of their correction. Furthermore, he delivered a second presentation from his team regarding the impact of fact-checking integrity on public trust. Markus Reiter-Haas from Graz University of Technology and Beate Klosh from the University of Graz, Austria, discussed polarisation in public opinion across different topics of misinformation. Lastly, Alicia Bargar and Amruta Deshpande explored the issue of affordances across different platforms and how this corresponds to different types of vulnerability to misinformation.

The second part of the workshop included a hands-on activity allowing for deeper discussions. A scenario was presented to the participants according to which citizens, journalists and policymakers needed support to distinguish fact from fiction in the context of COVID-19 “infodemic”. Following, they were invited to reflect on the existing best tools and identify their limits. The discussion showed that participants generally referred to two types of tools. Tools that assist users assessing information trustworthiness based on specific characteristics, or that direct them to trustworthy sources, or that provide information cascade (mainly image or film) were brought forward. At the same time, the benefits of tools that enable social media users to think before they share encouraging them to critically engage with information were discussed. The limits of these tools focused on the automation technologies used. Furthermore, it was noted that such tools can still be complex for the average social media users and demand a level of digital literacy.

The last part of the workshop was dedicated to synergies and collaborations among the participants. Potential research project ideas were discussed. Participants also welcomed the invitation to contribute to the EUNOMIA’s edited volume. The book will focus on issues around human and societal factors of misinformation and approaches and limitations of sociotechnical solutions.

Fighting and coping with misinformation in pandemic crises; COVINFORM Project kicks off featuring two EUNOMIA partners

December 22nd, 2020 by

COVID-19 has been categorised as an infodemic by WHO. It is the first pandemic where social media has been used on such a wide scale to both share protective information and also false information, including misinformation and disinformation. Those groups that are recognised as most vulnerable to COVID-19 may also be most vulnerable to believing and engaging with misinformation (Vijaykumar, 2020). As responses to COVID-19 misinformation has resulted in injuries and fatalities, it is important to address this (Coleman, 2020).

November 2020 saw the EC funded COVINFORM project (Grant Agreement No. 101016247) kick off. The three-year project focuses on analysing and understanding the impact of COVID-19 responses on vulnerable and marginalised groups. COVINFORM features two EUNOMIA partners, Trilateral Research and SYNYO, who will draw on their expertise and knowledge gained during the EUNOMIA project to develop guidance and recommendations for designing effective COVID-19 communication and combating misinformation.

In response to this challenge, WP7 of the COVINFORM project focuses on inclusive COVID-19 communication for behaviour change and misinformation. It will conduct an in-depth analysis of malinformation, disinformation and misinformation to identity insights on how misinformation might affect different groups differently and produce recommendations to fight and cope with misinformation during COVID-19 and future pandemic crises.

For further information, please visit the project website ( or follow the project on Twitter (                                                                                                                                        

COVINFORM is one of 23 new research projects funded by the European Commission with a total of €128 million to address the continuing coronavirus pandemic and its effects. The press release covering the project’s launch is available here.

EUNOMIA at the Industry Forum of GlobeCom 2020

December 22nd, 2020 by

In the era of COVID-19 pandemic, social media have become a dominant, direct and highly effective form of news generation and sharing at a global scale. This information is not always trustworthy as exemplified by the wide spread of misinformation that proved dangerous for public health. Prof. Charalampos Patrikakis from the University of West Attica -partner of EUNOMIA project- co-organised an event focusing on “Fighting Misinformation on Social Networks” at the Industry Forum session of the Global Communications Conference 2020. GlobeCom2020 is one of the IEEE Communications Society’s two flagship conferences dedicated to driving innovation in nearly every aspect of communications.

The event included presentations by academics and industry representatives followed by an open discussion. Prof. Patrikakis delivered a presentation on “EUNOMIA project: a decentralized approach to fighting fake news”. His presentation referred to the concept of EUNOMIA on the adaptation of information hygiene routines for protection against the ‘infodemic’ of rapidly spreading misinformation. Moreover, EUNOMIA presentation included a more extensive graphic description of the project’s toolkit with its four interrelated functional components: The information cascade, Human-as-Trust-Sensor interface, Sentiment and subjectivity analysis and the Trustworthiness scoring. Participants were also invited to register on EUNOMIA in order to see how this works in real-time.

The pathway to trustworthiness assessment; Sentiment Analysis identification

December 14th, 2020 by

As the amount of content online grows exponentially, new networks and interactions are also growing tremendously fast. EUNOMIA user’s trustworthiness indicators provide a boost towards a fair and balanced social network interaction.

Sentiment analysis is one of EUNOMIA’s trustworthiness indicators assisting users to assess the trustworthiness of online information. It relies on the automatic identification of the sentiment expressed in a user post (negative, positive, or neutral). A sentiment analysis algorithm employs principles from the scientific fields of machine learning and natural language processing. Current trends in the field include AI techniques that outperform traditional dictionary-based approaches and provide unparalleled performance.

Dictionary-based techniques work as follows:  A list of opinion words such as adjectives (i.e. excellent, love, supports, expensive, terrible, hate, complicated), nouns, verbs and word phrases constitute the prior knowledge for extracting the sentiment polarity of a piece of text. For example, in “I love playing basketball” a dictionary-based method would identify and consider the word “love” to infer the positive polarity of the expression.

Figure 1. Sentiment Analysis of user opinions

Unfortunately, these methods are unable to grasp long-range sentiment dependencies, sentiment fluctuations or opinion modifiers (i.e. not so much expensive, less terrible etc.) that exist in abundance in user-generated text.

Figure 2. Demo of how the core of the sentiment analysis component works in EUNOMIA.

We use two models that process user generated content in parallel. The first model relies on sentiment patterns to extract polarity. For example in “not so much expensive” the model would identify the relation between “not” and “expensive” and would assign positive polarity in  comparison to a dictionary-based method that would only rely on the negative word “expensive”.

The second model is an advanced machine learning model, that relies on a trained neural network and it can identify sentiment fluctuations of longer range. Therefore, the first model (pattern-based) relies on sentiment patterns to extract the sentiment orientation, while the second, relies on a neural network that is trained on labeled data and is capable of distinguishing between positive/neutral/negative text with high accuracy.

The output of both models is processed by an ensemble algorithm that decides on the final sentiment classification and the degree that the models are confident about their predictions.

The results of the sentiment analysis process provide one of EUNOMIA’s indicators. Sentiment and emotion in language is connected quite frequently with subjectivity and on many occasions with decietful information. EUNOMIA raises an alert and then the user, by consulting additional meta-information like EUNOMIA’s other indicators can investigate the content further and decide if it is valid and can be safely consumed or shared further to the community.

Pantelis Agathangelou, PhD Candidate, University of Nicosia

The featured photo is by Domingo Alvarez E on Unsplash