kerry.turcsi – Jean Golding Institute News

Meet the Ask-JGI team – Part 1 of 2

Posted on 22 January 202522 January 2025 by kerry.turcsi

All University of Bristol researchers (from PhD student and up) are entitled to a day of free data science support from the Ask-JGI helpdesk. Just email ask-jgi@bristol.ac.uk with your query and one of our team will get back to you to see how we can support you. You can see more about how the JGI can support data science projects for University of Bristol based researchers on our website (https://www.bristol.ac.uk/golding/supporting-your-research/data-science-support/).

The new Ask-JGI helpdesk cohort started in September 2024 and have been busy answering queries from researchers across the university! Meet some of the team below:

Mirah Zhang (she/her) – Ask-JGI PhD Student

Mirah Zhang, PhD candidate in Geographic Data Science in the School of Geographical Sciences

I am currently a PhD candidate in Geographic Data Science in the School of Geographical Sciences. My PhD work is methodologically focused. It involves elements of counterfactual prediction, and information theory based causal discovery. While a big part of causal inference is ‘normal’ statistics, I am particularly interested in scenarios where standard statistical models struggle in handling causal relations entangled with spatial structures.

Joining the Ask-JGI team has been an amazing opportunity for me to interact with researchers from a wide range of different backgrounds, and in different stages of their research. I am constantly learning on the job, not just acquiring new skills but also whole new perspectives!

Over the past few months, I have come to the understanding that there is more value to our work here than the code solutions we provide. It is an empowering experience, being able to interact with people, to empathize, and to lift them with the skills I have. It also gives me a sense of pride, being part of the stubborn human element in data science/AI that cannot be automated away. All of these have made my Ask-JGI role a uniquely fulfilling experience both academically and at a personal level.

Tao Zhou (he/him) – Ask-JGI PhD Student

Tao Zhou, PhD student in Advanced Quantitative Methods in the School of Geographical Sciences

I’m a final-year PhD student in Advanced Quantitative Methods in the School of Geographical Sciences, where my research focuses on the socio-economic determinants of health, especially health inequalities from a life-course and geographical perspective. Methodologically, I am mainly interested in Econometrics, structural equation modelling, multilevel modelling and survival analysis. In the meantime, I’m also passionate about exploring the variations and combinations of these models, such as latent growth curve modelling, intersectional MAIHDA, and longitudinal age-period-cohort analysis with spatial effects. Before the doctoral journey, I’ve got my BSc degree in Economics and MSc degree in Social Statistics.

As a member of the Ask-JGI team, I really enjoy discussing with researchers from a variety of disciplines across the university about their projects. These interactions help resolve their queries, while at the same time enhancing my own understanding of particular research areas.

The Ask-JGI helpdesk has created a platform for interdisciplinary communication through data science, which I highly recommend if you have any relevant enquiries or would like to apply to join our team for the next cohort.

Yueying Li (she/her) – Ask-JGI PhD Student

Yueying Li, PhD student in Population Health Sciences in the Bristol Medical School

I joined the Ask-JGI team as a PhD student in Population Health Sciences. Over the course of my academic journey, I’ve progressively narrowed my focus from public health during my bachelor’s, to epidemiology in my master’s, and now to genetic epidemiology for my PhD. This field deals with vast amounts of data, and leveraging data science techniques for efficient management and analysis can make a tremendous impact.

Before applying for this position, I heard glowing recommendations from colleagues and former Ask-JGI helpers, and I’m happy to say the experience has been incredibly rewarding. It’s a fantastic opportunity to sharpen my coding skills and refresh my statistical knowledge. During my education, I learned tools like SPSS, SAS, Stata, R, and Python, but not all of them are frequently used in my projects. Working at the Ask-JGI helpdesk has allowed me to hone those skills and expand my expertise. Beyond the technical growth, one of the most exciting parts of the job is engaging with researchers from diverse disciplines. It’s inspiring to contribute to their fascinating and valuable projects while learning from their unique perspectives. It is even more beneficial to do things in a team where everyone is talented, supportive, and respectful.

Dan Collins (he/him) – Ask-JGI Coordinator

Dan Collins, PhD student on the Interactive AI CDT in the School of Computer Science

I’m currently in the final year of my PhD with the Interactive AI CDT. While my research involves abstract simulation experiments and exploring conflicts and cooperation in populations of AI agents, I have a keen interest in the broader applications and impact of data science in the real world. Working with Ask-JGI has been a fantastic opportunity to explore this interest further.

I joined Ask-JGI last year as a student data scientist and had a great experience in the role. I’ve particularly enjoyed the collaborative nature of the work, and the exposure it has given me to different data science techniques and research problems across a variety of specialisms. This year, I’ve had the opportunity to continue working with Ask-JGI as a Coordinator. In this role, I’ve been able to draw on my experiences to help support a new team of Ask-JGI PhD students, while continuing to deliver data science support through the helpdesk.

I believe Ask-JGI is a truly valuable program. It enables PhD students with data science expertise to develop their skills and gain experience collaborating on interdisciplinary research, and it encourages researchers at the University to explore how data science techniques can be used to support their work.

If you’re a PhD student interested in joining the Ask-JGI team (or you know someone who might be good for it), we will do recruiting for the next academic year in summer of 2025 so keep an eye on the JGI mailing list for when we have our recruiting call. We recruit a new cohort every year but do not accept speculative applications outside of the recruiting call.

PhD Connect Conference

Posted on 10 December 202411 December 2024 by kerry.turcsi

Our Turing Liaison team recently funded a number of PhD students to go to the 2024 Alan Turing PhD Connect Conference. This is one of the range of approaches we are taking to bridging the gap between the Turing’s goals and the University’s research and academics who reflect these goals.

Attendees sat around circular tables with sheets of paper and pens on the table — *Attendees at a PhD Connect conference. Photo provided by Jingrong Bai*.

Supporting PhD students to make connections and discover new collaborations through the Turing will hugely benefit students and the wider data science and AI community, and is an important part of our objective. Below are some statements from the students we funded about their experience at the conference.

Damien Wang

I am Damien, a first-year PhD student from University of Bristol and SWDTP who specializing in psychology and artificial intelligence. The past two days at PhD Connect 2024 have been incredibly fulfilling. I had the opportunity to explore a wide range of PhD projects in AI and data science, engaging in discussions with other attendees and collaboratively tackling problems by leveraging our diverse backgrounds.

Conversations with peers and insights from the panel discussions were truly enlightening. I was also fortunate to represent my group during the Mini-DSG session and deliver my own poster presentation. These experiences have boosted my confidence and skills in presenting, and I’m grateful for the valuable feedback I received on my research.

This two-day journey has inspired me to push forward with even greater motivation. A heartfelt thanks to the Alan Turing Institute and everyone I met along the way!

Ming Chen

The PhD Connect 2024 conference was an incredible opportunity to engage with peers, learn from industry experts, and explore real-world applications of data science and AI. My research interests include learning sciences and emerging technologies in language learning. I would say that one of the highlights for me was participating in group research discussions, which broadened my understanding of AI’s role in addressing societal challenges.

I also appreciated the networking opportunities and the chance to discuss my research with fellow attendees and professionals from diverse sectors. Another interesting part of the conference is the Research Karaoke, which is a great experience for people to have fun and practise doing presentations.

Jizhao Niu

I am grateful to The Jean Golding Institute for funding my attendance at the conference. It was a fantastic opportunity to meet many PhD students from Bristol and beyond, engaging in discussions on health sciences-related projects.

A highlight for me was the training session on how to pitch research effectively, which provided valuable insights and practical skills. We worked as a team to sell an item to other groups, which was both enjoyable and educational.

I learned the importance of tailoring research presentations to audiences with diverse backgrounds — a skill I look forward to applying in the future!

Jingrong Bai

During the conference, we got insightful points on AI-human by Piotr Mirowski from DeepMind. Then, we interacted with the group work and presented karaoke, which was good for us to connect with other PhD students across the UK, also, learned how to prepare a good presentation by Beatriz Costa Gomes. Last but not the least, we shared our research ideas through the poster session. All in all, it is a valuable experience for me to know the AI field and meet all of the awesome people, really appreciate all of the speakers, organizers and students.

Jingrong Bai (left) standing in front of a poster with two other individuals discussing the posters on display — *Jingrong Bai (second on the left) with other PhD students at a networking sessio*n.

Zia Saylor

Zia Taylor (left), Kerstin Nothnagel (centre) and Michael Rumbelow (right) at PhD Connect — *Zia Saylor (left), Kerstin Nothnagel (centre) and Michael Rumbelow (right) at PhD Connect*.

Perhaps my favorite session was the one on day 2 morning of the conference when we discussed the principles of a good academic presentation. Focusing on basics like practice, maintaining relevancy to the audience, and ensuring that materials were packaged in an alluring way were key methods discussed. Looking at the AI aspect of our learning opportunities, much of the conference consisted of hands-on opportunities to engage with the materials, from designing a workflow that would integrate AI into academia without infringing on the rights and words of academics to developing a mechanism to integrate data on building pricing into an AI cost estimation algorithm that could be made. This enabled us as students to learn more about AI in its many forms and potential for interdisciplinary applications.

Jay Liu

It has been a wonderful journey for me to attending the 2024 Alan Turing AI PhD Conference at Horizon Leeds. It is my first time travelling to Leeds, a fantastic city with fancy malls and restaurants. I am grateful for the great opportunity and generous funding for the program!

I am a PhD student in Finance at the University of Bristol Business School, focusing on understanding the effects of AI and algorithmic decision making in the financial markets. I believe the conference can further improve my understanding on AI and the application of AI on interdisciplinary research!

Jay Liu standing in front of a digital screen showing a slide titled 'Welcome to the PhD Connect' — *Jay Liu standing in front of a digital screen at PhD Connect*.

Alan Turing Institute tote bag (right) featuring Alan Turing's face on it and Jay Liu's name badge (left) for PhD Connect — *Jay Liu standing in front of a digital screen at PhD Connect*.

Zhengzhe Peng

Numerous speakers standing at the front of the room in front of a slideshow projected on a wall — *Session from PhD connect with multiple speakers*.

Attending the PhD Connect Conference organized by the Alan Turing Institute was an enriching experience. I particularly appreciated the diverse perspectives shared during interdisciplinary discussions on data science applications. The keynote sessions inspired new ideas for integrating AI into my research, while the networking opportunities allowed me to connect with peers tackling similar challenges. I gained valuable insights into emerging methodologies and practical approaches that will enhance my PhD work.

Boyang Yu

This conference let me engage with the Mini-data group to explore data science applications in real-world challenges, which is what I’m doing as a PhD. I enhanced my presentation skills and learned to communicate complex ideas to a broader audience, inspired by a standout example from the presenter (Dr Beatriz Costa Gomes). I saw some very nice posters and great to have a picture with one of my most favourite poster (and its owner).

Female speaker on stage behind a lectern with a projected slide behind them showing 'Today's agenda' with timings and session titles — *Damien Wang (left) and Boyang Yu (right) at a poster session at PhD Connect*.

Ding Li

Attending the 2024 Turing Phd connect conference is such an unforgettable experience. I have met a bunch of bioinformatics students from various universities and institutions sharing their research with AI and Machine Learning. The poster and presentation session left me with impression on how research from other fields could help with my own PhD project. During the session, I discussed with Mr Muizz who is also from University of Bristol, but another school of Engineering Mathematics, and heard about how he applied AI on topology of insects’ wings in traditional species classification and phylogeny. It would never happen if there were no such an opportunity.

Ding Li standing in front of a poster with two other male individuals conversing about the poster — *Ding Li (Left) listening to talks given by data scientist Dr Piotr Mirowskifrom Google Deepmind*.

Kerstin Nothnagel

Attending the Alan Turing Institute PhD Connect Conference was an incredible experience. Highlights included Dr Piotr Mirowski’s inspiring keynote on human-machine collaboration and the ‘Mini Data Study Group,’ where we tackled real-world challenges like ICU surge prediction and cancer forecasting.

This event was a perfect prelude to my upcoming ATI funded UK-Italy Trustworthy AI Visiting Researcher Programme in Milan, where I’ll collaborate with global researchers to explore ‘Global AI Policies and Regulations and Their Impact on Healthcare.’ The project is reinforced by the importance of unifying AI policies to ensure technology benefits everyone equally, closing economic gaps rather than widening them.

Successful Seedcorn Awardees 2024-2025

Posted on 6 November 20246 November 2024 by kerry.turcsi

The Jean Golding Institute Seedcorn Funding is a fantastic opportunity to develop multi and interdisciplinary ideas while promoting collaboration in data science and AI.  We are delighted that a new cohort of multidisciplinary researchers has been supported through this funding.

Leighan Renaud – Building a Folk Map of St Lucia

Dr. Leighan Renaud is a lecturer in Caribbean Literatures and Cultures in the Department of English. Her research interests include twenty-first century Caribbean fiction, mothering and motherhood in the Caribbean, folk and oral traditions in the Anglophone Caribbean, and creative practices of neo-archiving.

Louise AC Millard – Using digital health data for tracking menstrual cycles

Dr. Louise Millard is a Senior Lecturer in Health Data Science in the MRC Integrative Epidemiology Unit (IEU) at the University of Bristol. Following an undergraduate Computer Science degree and MSc in Machine Learning and Data Mining, they completed an interdisciplinary PhD at the interface of Computer Science and Epidemiology. Their research interests lie in the development and application of computational methods for population health research, including using digital health and phenotypic data, and statistical and machine learning approaches.

Laura Fryer – Visualisation tool for Enhancing Public Engagement Using Supermarket Loyalty Card Data

Laura is a senior research associate in the Digital Footprints Lab based within the Bristol Medical School. Their aim is to use novel data to unlock insights into behavioural science for the purposes of public good. Laura is particularly passionate about broadening the public’s understanding of digital footprint data (e.g. from loyalty cards, bank transactions or wearable technology such as a smart watch) and demonstrating how vital it can be in developing our understanding of population health within the UK and beyond. Laura’s project is focused on developing a data-visualisation tool that will support public engagement activities and provide a tangible representation of the types of data that we use – building further trust between the public and scientific researchers.

Nicola A Wiseman – Cellular to Global Assessment of Phytoplankton Stoichiometry (C-GAPS)

Dr. Nicola Wiseman is a Research Associate in the School of Geographical Sciences. They received their PhD in Earth System Science from the University of California, Irvine, where they specialized in using ocean biogeochemical models to investigate the impacts of phytoplankton nutrient uptake flexibility on ocean carbon uptake. They also are interested in using statistical methods and machine learning to better understand the interactions between marine nutrient and carbon cycles, and the role of these interactions in regulating global climate.

George Sains – Collecting & Analysing Multilingual EEG Data

George Sains is a Doctoral Teaching Associate in the Neural Computation research group at the School of Computer Science. Their research is focused on the overlap between Computer Science, Neuroscience, and Linguistics. George has worked on developing models to help understand how linguistic traits have evolved. More recently, they have been using Bayesian modelling to find patterns between grammar and neurological response and are now focused on using Electroencephalography experimentation to explore the relationship between linguistic upbringing and how the brain processes language.

Alex Tasker – Building a Strategic Critical Rapid Integrated Biothreat Evaluation (SCRIBE) data tool for research, policy, and practice

Dr. Tasker is a Senior Lecturer at the University of Bristol, a Research Associate at the KCL Conflict Health Research Group and Oxford Climate Change & (In)Security (CCI) project, and a recent ESRC Policy Fellow in National Security and International Relations. Dr. Tasker is an interdisciplinary researcher working across social and natural sciences to understand human-animal-environmental health in situations of conflict, criminality, and displacement using One Health approaches. Alongside this core focus, Dr. Tasker’s work also explores emerging areas of relevance to biosecurity and biothreat including engineering biology, antimicrobial resistance, subterranean spaces, and the use of new forms of evidence and expertise in a rapidly changing world for climate, security, and defense.

Exploring the Impact of Medical Influencers on Health Discourse Through Socio-Semantic Network Analysis

Posted on 2 October 2024 by kerry.turcsi

JGI Seed Corn Funding Project Blog 2023/24: Roberta Bernardi

This Photo by Unknown Author is licensed under CC BY-NC-ND

Project Background

Medical influencers on social media shape attitudes towards medical interventions but may also spread misinformation. Understanding their influence is crucial amidst growing mistrust in health authorities. We used a Twitter dataset of the top 100 medical influencers during Covid-19 to construct a socio-semantic network, mapping both medical influencers’ identities and key topics. Medical influencers’ identities and the topics they use to represent an opinion serve as vital indicators of their influence on public health discourse. We developed a classifier to identify influencers and their network of actors, used BERTopic to identify influencers’ topics, and mapped their identities and topics into a network.

Key Results

Identity classification

Most Twitter bios include job titles and organization types, which often have similar characteristics. So, we used a machine learning tool to see how accurately we could predict someone’s job based on their Twitter bio. Our main question is: How well can we guess occupations from Twitter bios using the latest techniques in Natural Language Processing (NLP), like few-shot classification and pre-trained sentence embeddings? We manually coded a training set of 2000 randomly selected bios from the to 100 medical influencers and their followers. Table 1 shows a sample of 10 users with (multi-)labels.

Table of users and their multi-labels — *Table 1. Users and their multi-labels*

We used six prompts to classify the identities of medical influencers and other actors in their social network. The ensemble method, which combines all prompts, demonstrated superior performance, achieving the highest precision (0.700), recall (0.752), F1 score (0.700), and accuracy (0.513) (Table 2).

Table of prompts and their identities classification — *Table 2. Comparison of different prompts for the identities classification*

Topic Modelling

We used BERTopic to identify topics from a corpus of 424,629 tweets posted by the medical influencers between December 2021 and February 2022 (Figure 1).

Coloured scatter graph of medical influencer topics — *Figure 1. Map of medical influencers’ topics*

In total, 665 topics were identified. The most prevalent topic is related to vaccine hesitancy (8919 tweets). The second most significant topic focuses on equitable vaccine distribution 6860 tweets. Figures 2a and 2b illustrate a comparison between the top topics identified by Latent Dirichlet Allocation (LDA) and those by BERTopic.

Word map of LDA top 5th topics on the left and bar charts of BERTopic top 8th topics on the right — *Figure 2. Comparisons of LDA topics and BERTopic topics*

The topics derived from LDA appear more general and lack specific meaning, whereas the topics from BERTopic are notably more specific and carry clearer semantic significance. For example, the BERTopic model shows either the “Hesitancy” or the “Equity” of the vaccine (topic 0, 1), while the LDA model only provides general topic information (topic 0).

Table 3 shows the three different topic representations generated from the same clusters by three different methods: Bag-of-Words with c-TF-IDF, KeyBERTInspired and ChatGPT.

Table of comparison of three different topic representations methods of BERTopic — *Table 3: Comparison of three different topic representations methods of BERTopic*

The Keyword Lists from Bag-of-Words with c-TF-IDF and KeyBERTInspired provide quick information about the content of the topic, while the narrative Summaries from ChatGPT offer a human-readable summary but may sacrifice some specific details that the keyword lists will provide. BERTopic captures deeper text meanings, essential for understanding conversation context and providing clear topics, especially in short texts like social media posts.

Mapping Identities and Topics in Networks

We mapped actors’ identities and the most prevalent topics from their tweets into a network (Figure 3).

*Figure 3. Network representation of actors’ identities and topics*

Each user node features an attribute detailing their identities, which defines the influence of medical influencers within their network and how their messages resonate across various user communities. This visualization reveals their influence and how they adapt discourse for different audiences based on group affiliations. It aids in exploring how the perspectives of medical influencers on health issues proliferate across social media communities.

Conclusion

Our work shows how to identify who medical influencers are and what topics they talk about. Our network representation of medical influencers’ identities and their topics provides insights into how these influencers change their messages to connect with different audiences. First, we used machine learning to categorize user identities. Then, we used BERTopic to find common topics among these influencers. We created a network map showing the connections between identities, social interactions, and the main topics. This innovative method helps us understand how the identities of medical influencers affect their position in the network and how well their messages connect with different user groups.

Contact details and links

For further information or to collaborate on this project, please contact Dr Roberta Bernardi (email: roberta.bernardi@bristol.ac.uk)

Acknowledgement

This blog post’s content is based on the work published in Guo, Z., Simpson, E., Bernardi, R. (2024). ‘Medfluencer: A Network Representation of Medical Influencers’ Identities and Discourse on Social Media,’ presented at epiDAMIK ’24, August 26, 2024, Barcelona, Spain

Foodscapes: visualizing dietary practices on the Roman frontiers

Posted on 26 September 202426 September 2024 by kerry.turcsi

JGI Seed Corn Funding Project Blog 2023/24: Lucy Cramp, Simon Hammann & Martin Pitts

*Table laid out with Roman pottery from Vindolanda ready for sampling for organic residue analysis as part of our ‘Roman Melting Pots’ AHRC-DFG funded project*

The extraction and molecular analysis of ancient food residues from pottery enable us to reconstruct the actual uses of vessels in the past. This means we can start to build up pictures of dietary patterns in the past, including foodways at culturally diverse communities such as the Roman frontiers. However, there remains a challenge in how we can interpret these complex residues, and both visualise and interrogate these datasets to explore use of resources in the past.

Nowadays, it is commonplace to extract organic residues from many tens, if not hundreds, of potsherds; within each residue, and especially using cutting-edge high-resolution mass spectrometric (HRMS) techniques, there might be several hundred compounds present, including some at very low abundance. Using an existing dataset of gas chromatography-high resolution mass spectrometric data from the Roman fort and associated settlement at Vindolanda, this project aimed to explore methods through which these dietary information could be spatially analysed across an archaeological site, with a view to developing methods that could be applied on a range of scales, from intra-site through to regional and even global. It was hoped that it would be possible to display the presence of different compounds in potsherds recovered from different parts of a site that are diagnostic of particular foodstuffs, in order to spatially analyse the distribution of particular resources within and beyond sites.

*A fragment from a Roman jar that was sampled from Vindolanda for organic residue analysis as part of our ‘Roman Melting Pots’ AHRC-DFG funded project*

The project started by processing a pilot dataset of GC-HRMS data from the site of Vindolanda, following a previously-published workflow (Korf et al. 2020). These pottery sherds came from different locations at the fort, occupied by peoples of different origins and social standings. This included the praetorium (commanding officer’s house), schola (‘officers’ mess’), infantry barracks (occupied by Tungrians, soldiers from modern-day Belgium and Netherlands), and the non-military ‘vicus’ outside of the fort walls likely occupied by locals, traders and families. Complex data, often containing several hundred compounds per residue were re-integrated using open-source mass spectrometry data processing software MZ Mine, supported by our collaborator from MZ IO gmbh, Dr Ansgar Korf. This produced a ‘feature list’ of compounds and their intensities across the sample dataset. This feature list was then presented to Emilio Romero, a PhD student in Translational Health Sciences, who worked as part of the Ask-JGI helpdesk to support academic researchers on projects such as these. Emilio developed data matrices and performed statistical analyses to identify significant compounds of interest that were driving differences between the composition of organic residues from different parts of the settlement. This revealed, for example, that biomarkers of plant origin appear to be more strongly associated with pottery recovered from inside the fort compared with the vicus outside the fort walls. He was then able to start exploring ways to spatially visualize these data, with input from Léo Gorman, a data scientist from the JGI, and Levi Wolf from the School of Geographical Sciences. Emilio says:

‘Over the past year, my experience helping with the Ask-JGI service has been truly rewarding. I was very excited to apply as I wanted to gain more exposure to the world of research in Bristol, meet different researchers and explore with them different ways of working and approaching data.

One of the most challenging projects was working with chemometric concentrations of different chemical compound residues extracted from vessels used in ancient human settlements. This challenge allowed me to engage in dialogue with specialists in the field and work in a multidisciplinary way in developing data matrices, extracting coordinates and creating maps in R. The most rewarding part was being able to use a colour scale to represent the variation in concentration of specific compounds in settlements through the development of a Shiny application in R. It was certainly an invaluable experience and a technique I had never had the opportunity to practice before.’

This work is still in progress, but we have planned a final workshop that will take place in mid-November. Joining us will be our project partners from the Vindolanda Trust, as well as colleagues from across the Roman Melting Pots project, the JGI and the University of Bristol. A funding application to develop this exploratory spatial analysis has been submitted to the AHRC.

Contact details and links

You can find out more about our AHRC-DFG funded project ‘Roman Melting Projects’ and news from this season’s excavations at Vindolanda and its sister site, Magna.