Multidisciplinary International Symposium on Disinformation in Open Online Media

Conference Information
Name: Multidisciplinary International Symposium on Disinformation in Open Online Media
Acronym: MISDOOM
Date: 21 September 2021 - 22 September 2021

Articles from this conference

Published: 15 September 2021
Algorithmic Game Theory pp 33-49;

We propose an integration of Non-negative Matrix Factorisation, Sentiment analysis and Structural Break Models to identify significant topical shifts on the social media platform Twitter. For the topic modelling, we compare Latent Dirichlet Allocation and Non-negative Matrix Factorization in terms of their applicability to short text documents. The extraction of sentiment is done by the rule-based VADER model. Structural breaks in the relative frequency and daily sentiments of topics over time are identified with the Bai-Perron model. Combining these methods, we provide a valuable and easy to use exploratory tool for social scientists to study the discourse on Twitter over time. Detecting statistically significant shifts in topics over time enables researchers to perform statistical inference and test hypotheses about the discourse on Twitter. The framework is implemented efficiently to ensure that it can be used on average consumer hardware in a reasonable amount of time. A case study with COVID-19 related tweets in the UK is provided. Our method is validated by linking the topical shifts to real world events by the use of the timestamps of the COVID-19 related tweets.
, Kilian Müller, Chantal Kelm, Dennis Assenmacher,
Published: 15 September 2021
Algorithmic Game Theory pp 112-127;

Online comment sections revolutionised the participatory discourse as enabled by news media, limiting the hurdles to participate and speeding up the process from submission to publication. What was initially meant to strengthen public debates and democracy turned out to suffer from abusive use: Be it insulting journalists, posting misinformation, or pure hate. While many publishers and journalists are eager to create an engaged audience, user-generated content typically does not create direct revenues. However, keeping the abuse at bay is often obligatory from an ethical and legal perspective and can be costly. Germany has been highly affected by abuse in combination with strict regulation, leading to the shutdown of many comment sections. While reports in 2014 indicated closure rates of 50% and more, a structured overview of the situation in 2020/21 is missing. We conducted a structured assessment of 114 German newspaper websites containing all major outlets to account for this. Our analyses indicate that the deteriorating trend regarding the availability of comment sections slowed down in Germany. However, there are still open issues such as a high number of outlets using post-moderation and limited audience participation options. This provides a reference to researchers and practitioners working on (semi-) automated moderation systems regarding the expectable market and problem size.
Back to Top Top