Despite extensive research and development of tools technologies for misinformation tracking detection, we often find ourselves largely on the losing side battle against misinformation. In an era where poses a substantial threat to public discourse, trust in information sources, societal political stability, it is imperative that regularly revisit reorient our work strategies. While have made significant strides understanding how why spreads, must now broaden focus explore technology can...

Online enquiry communities such as Question Answering (Q&A) websites allow people to seek answers all kind of questions. With the growing popularity platforms, it is important for community managers constantly monitor performance their communities. Although different metrics have been proposed tracking evolution communities, maturity, process in which become more topic proficient over time, has largely ignored despite its potential help identifying robust In this paper, we interpret maturity...

The value of Question Answering (Q&A) communities is dependent on members the community finding questions they are most willing and able to answer. This can be difficult in with a high volume questions. Much previous has work attempted address this problem by recommending similar those already answered. However, approach disregards question selection behaviour answers how it affected factors such as recency reputation. In paper, we identify parameters that correlate analysing users'...

Nowadays, Question Answering (Q&A) websites are popular source of information for finding answers to all kind questions. Due this popularity it is critical help the identification best existing questions simplifying access relevant information.

Machine Learning (ML) algorithms are embedded within online banking services, proposing decisions about consumers' credit cards, car loans, and mortgages. These sometimes biased, resulting in unfair toward certain groups. One common approach for addressing such bias is simply dropping the sensitive attributes from training data (e.g. gender). However, can indirectly be represented by other maternity leave taken). This paper addresses problem of identifying that mimic a new based on...

Social media plays a vital role in information sharing during disasters. Unfortunately, the overwhelming volume and variety of data generated on social make it challenging to sieve through such content manually determine its relevancy. Most automated approaches classify crisis for relevancy are based classic statistical features. However, do not adapt well situations when applied new event, or language that model was trained on. In situations, training particular crises languages is viable...

Value of online Question Answering (Q&A) communities is driven by the question-answering behaviour its members. Finding questions that members are willing to answer therefore vital efficient operation such communities. In this paper, we aim identify parameters correlate with behaviours. We train different models and construct effective predictions using various user, question thread feature sets. show answering can be predicted a high level success.

Abstract Correcting misinformation is a complex task, influenced by various psychological, social, and technical factors. Most research evaluation methods for identifying effective correction approaches tend to rely on either crowdsourcing, questionnaires, lab‐based simulations, or hypothetical scenarios. However, the translation of these findings into real‐world settings, where individuals willingly freely disseminate misinformation, remains largely unexplored. Consequently, we lack...