1 code implementation • EACL 2021 • Ella Guest, Bertie Vidgen, Alexandros Mittos, Nishanth Sastry, Gareth Tyson, Helen Margetts
Online misogyny is a pernicious social problem that risks making online platforms toxic and unwelcoming to women.
1 code implementation • 28 Aug 2023 • Vahid Ghafouri, Vibhor Agarwal, Yong Zhang, Nishanth Sastry, Jose Such, Guillermo Suarez-Tangil
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.
1 code implementation • 16 Feb 2022 • Vibhor Agarwal, Sagar Joglekar, Anthony P. Young, Nishanth Sastry
We then use these embeddings to predict the polarity relation between a reply and the post it is replying to.
1 code implementation • 9 Mar 2018 • Shweta Bhatt, Sagar Joglekar, Shehar Bano, Nishanth Sastry
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
1 code implementation • 12 Sep 2019 • Aravindh Raman, Sagar Joglekar, Emiliano De Cristofaro, Nishanth Sastry, Gareth Tyson
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
1 code implementation • 3 Apr 2024 • Vibhor Agarwal, Aravindh Raman, Nishanth Sastry, Ahmed M. Abdelmoniem, Gareth Tyson, Ignacio Castro
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.
no code implementations • 3 May 2019 • Xuehui Hu, Nishanth Sastry
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.
no code implementations • 23 Apr 2020 • Pushkal Agarwal, Kiran Garimella, Sagar Joglekar, Nishanth Sastry, Gareth Tyson
In the case of images containing text that cross language barriers, we see that language translation is used to widen the accessibility.
no code implementations • 15 Jun 2022 • Pushkal Agarwal, Nishanth Sastry, Edward Wood
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.
no code implementations • 16 Nov 2022 • Vibhor Agarwal, Anthony P. Young, Sagar Joglekar, Nishanth Sastry
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.
no code implementations • 20 Dec 2022 • Wenjie Yin, Vibhor Agarwal, Aiqi Jiang, Arkaitz Zubiaga, Nishanth Sastry
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.
no code implementations • 21 Oct 2023 • Vibhor Agarwal, Yu Chen, Nishanth Sastry
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.
no code implementations • 21 Oct 2023 • Vibhor Agarwal, Yu Chen, Nishanth Sastry
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.