Search Results for author:
Found 13 papers, 6 papers with code
An Expert Annotated Dataset for the Detection of Online Misogyny
Online misogyny is a pernicious social problem that risks making online platforms toxic and unwelcoming to women.
AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics
The introduction of ChatGPT and the subsequent improvement of Large Language Models (LLMs) have prompted more and more individuals to turn to the use of ChatBots, both for information and assistance with decision-making.
GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates
We then use these embeddings to predict the polarity relation between a reply and the post it is replying to.
Illuminating an Ecosystem of Partisan Websites
This paper aims to shed light on alternative news media ecosystems that are believed to have influenced opinions and beliefs by false and/or biased news reporting during the 2016 US Presidential Elections.
Social and Information Networks
Challenges in the Decentralised Web: The Mastodon Case
The Decentralised Web (DW) has recently seen a renewed momentum, with a number of DW platforms like Mastodon, Peer-Tube, and Hubzilla gaining increasing traction.
Networking and Internet Architecture Cryptography and Security Computers and Society
Decentralised Moderation for Interoperable Social Networks: A Conversation-based Approach for Pleroma and the Fediverse
Recent work has exploited the conversational context of a post to improve this automatic tagging, e. g. using the replies to a post to help classify if it contains toxic speech.
Characterising Third Party Cookie Usage in the EU after GDPR
We find that on average the number of third parties dropped by more than 10% after GDPR, but when we examine real users' browsing histories over a year, we find that there is no material reduction in long-term numbers of third party cookies, suggesting that users are not making use of the choices offered by GDPR for increased privacy.
Characterising User Content on a Multi-lingual Social Network
In the case of images containing text that cross language barriers, we see that language translation is used to widen the accessibility.
Discovery of the Content and Engagement with the Content
More recently, in an effort to further improve transparency and citizen engagement, the UK Parliament started publishing videos of these debates and meetings itself, and tweeting details of debates as they happened.
A Graph-Based Context-Aware Model to Understand Online Conversations
We evaluate GraphNLI on two such tasks - polarity prediction and misogynistic hate speech detection - and found that our model consistently outperforms all relevant baselines for both tasks.
AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection
During training, the model associates annotators with their label choices given a piece of text; during evaluation, when label information is not available, the model predicts the aggregated label given by the participating annotators by utilising the learnt association.
GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding
Specifically, we design two novel algorithms that utilise both the graph structure of the online conversation as well as the semantic information from individual posts for retrieving relevant context nodes from the whole conversation.
HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models
We develop 4 different prompts based on task description, hate definition, few-shot demonstrations and chain-of-thoughts for comprehensive experiments and conduct experiments on open-source LLMs such as LLaMA-1, LLaMA-2 chat, Vicuna as well as OpenAI's GPT-3. 5.
