X Close

DIS Research Seminars



Archive for January, 2024

Research Talk by Abul Hasan

By Antonios Bikakis, on 25 January 2024

Incorporating Dictionaries into a Neural Network Architecture to Extract COVID-19 Medical Concepts From Social Media

The talk was delivered on 24 January 2024 by Dr. Abul Hasan, a postdoctoral research fellow at the UCL Institute of Health Informatics, as part of the DIS research seminars series.

We investigate the potential benefit of incorporating dictionary information into a neural network architecture for natural language processing. In particular, we make use of this architecture to extract several concepts related to COVID-19 from an on-line medical forum. We use a sample from the forum to manually curate one dictionary for each concept. In addition, we use MetaMap, which is a tool for extracting biomedical concepts, to identify a small number of semantic concepts. For a supervised concept extraction task on the forum data, our best model achieved a macro F1 score of 90%. A major difficulty in medical concept extraction is obtaining labelled data from which to build supervised models. We investigate the utility of our models to transfer to data derived from a different source in two ways. First for producing labels via weak learning and second to perform concept extraction. The dataset we use in this case comprises COVID-19 related tweets and we achieve an F1 score 81% for symptom concept extraction trained on weakly labelled data. The utility of our dictionaries is compared with a COVID-19 symptom dictionary that was constructed directly from Twitter. Further experiments that incorporate BERT and a COVID-19 version of BERTweet demonstrate that the dictionaries provide a commensurate result. Our results show that incorporating small domain dictionaries to deep learning models can improve concept extraction tasks. Moreover, models built using dictionaries generalize well and are transferable to different datasets on a similar task.

Research Talk by Photini Vrikki

By Antonios Bikakis, on 19 January 2024

(Re)Shaping Digital Humanities through Environmental Justice

The talk was delivered on 29 November 2023 by Dr. Photini Vrikki, member of the UCL Centre for Digital Humanities, as part of the DIS research seminars series.

As a field in constant transformation and expansion, Digital Humanities takes a broad shape to accommodate interdisciplinarity yet be grounded in the Humanities. This interdisciplinarity allows us the space to question some of the practices and processes we often consider fixed in academia. In this talk I will refer to a dual shift in DH as a call to shape and reshape the field vis-à-vis environmental justice. First, shaping includes building common, sustainable, intentional, and collective connections and speaking up for how things could be different, and how uncommon and complex tasks such as demanding for more resources and institutional changes can benefit the field. Second, I point towards the need for action in the face of parts of Digital Humanities that need to be reshaped, such as innovation and global education, to discuss the entanglement of the field with the ecological crisis. Ultimately, the paper promotes environmentally aware DH practices that bring environmental justice into play.

Research Talk by Anthony Hunter

By Antonios Bikakis, on 19 January 2024

Towards Computational Persuasion for Behaviour Change Applications.

The talk was delivered on 22 November 2024 by Prof. Anthony Hunter, Professor of Artificial Intelligence in the Department of Computer Science, University College London, as part of the DIS research seminars series.

The aim of behaviour change is to help people to change aspects of their behaviour for the better (e.g., to decrease calorie intake, to drink in moderation, to take more exercise, to complete a course of antibiotics once started, etc.). Recent developments in computational modelling of argument (a subfield of AI) are leading to technology for persuasion that can potentially be harnessed in behaviour change applications. Using this technology, a software system and a user can exchange arguments in a dialogue. So the system gains information about the user’s perspective, provides arguments to fill gaps in the user’s knowledge, and attempts to overturn misconceptions held by the user. Our work has focused on modelling the beliefs and concerns of the user, and harnessing these to make the best choices of move during the dialogue for persuading the user to change their behaviour. We have also been investigating how we can harness recent developments in large language models to provide a natural language interface to this technology. In this talk, I will provide an overview of our approach together with some promising preliminary results with participants.