Featured Post from Aston University

Aston University forensic linguistics experts partner in $11.3 million funding for authorship attribution research

Dec 7, 2022

4 min


  • Aston Institute for Forensic Linguistics (AIFL) is part of the project to infer authorship of uncredited documents based on writing style
  • AIFL’s Professor Tim Grant and Dr Krzysztof Kredens are experts in authorship analysis
  • Applications may include identifying counterintelligence risks, combating misinformation online, fighting human trafficking and even deciphering authorship of ancient religious texts.


Aston University’s Institute for Forensic Linguistics (AIFL) is part of the AUTHOR research consortium which has won an $11.3 million contract to infer authorship of uncredited documents based on the writing style.


The acronym stands for ‘Attribution, and Undermining the Attribution, of Text while providing Human-Oriented Rationales’. Worth $1.3 million, the Aston University part of the project is being led by Professor Tim Grant and Dr Krzysztof Kredens, who both are recognised internationally as experts in authorship analysis and who both engage in forensic linguistic casework as expert witnesses.


In addition to their recognised general expertise and experience in this area, Professor Grant has specific expertise in using linguistic analysis to enhance online undercover policing and Dr Kredens has led projects to develop authorship identification techniques involving very large numbers of potential authors.


The AUTHOR team is led by Charles River Analytics and is one of six teams of researchers that won The Human Interpretable Attribution of Text Using Underlying Structure (HIATUS) programme sponsored by the Intelligence Advanced Research Projects Activity (IARPA). The programme uses natural language processing techniques and machine learning to create stylistic fingerprints that capture the writing style of specific authors.


On the flip side is authorship privacy - mechanisms that can anonymize identities of authors, especially when their lives are in danger. Pitting the attribution and privacy teams against each other will hopefully motivate each, says Dr Terry Patten, principal scientist at Charles River Analytics and principal investigator of the AUTHOR consortium.


“One of the big challenges for the programme and for authorship attribution in general is that the document you’re looking at may not be in the same genre or on the same topic as the sample documents you have for a particular author,” Patten says. The same applies to languages: We might have example articles for an author in English but need to match the style even if the document at hand is in French. Authorship privacy too has its challenges: users must obfuscate the style without changing the meaning, which can be difficult to execute.”


In the area of authorship attribution, the research and casework experience from Aston University will assist the team in identifying and using a broad spectrum of authorship markers. Authorship attribution research has more typically looked for words and their frequencies as identifying characteristics. However, Professor Grant’s previous work on online undercover policing has shown that higher-level discourse features - how authors structure their interactions - can be important ‘tells’ in authorship analysis.


The growth of natural language processing (NLP) and one of its underlying techniques, machine learning, is motivating researchers to harness these new technologies in solving the classic problem of authorship attribution. The challenge, Patten says, is that while machine learning is very effective at authorship attribution, “deep learning systems that use neural networks can’t explain why they arrived at the answers they did.”


Evidence in criminal trials can’t afford to hinge on such black-box systems. It’s why the core condition of AUTHOR is that it be “human-interpretable.” Dr Kredens has developed research and insights where explanations can be drawn out of black box authorship attribution systems, so that the findings of such systems can be integrated into linguistic theory as to who we are as linguistic individuals.


Initially, the project is expected to focus on feature discovery: beyond words, what features can we discover to increase the accuracy of authorship attribution?


The project has a range of promising applications – identifying counterintelligence risks, combating misinformation online, fighting human trafficking, and even figuring out the authorship of ancient religious texts.


Professor Grant said: “We were really excited to be part of this project both as an opportunity to develop new findings and techniques in one of our core research areas, and also because it provides further recognition of AIFL’s international reputation in the field. Dr Kredens added: “This is a great opportunity to take our cutting-edge research in this area to a new level”.


Professor Simon Green, Pro-Vice-Chancellor for Research, commented: “I am delighted that the international consortium bid involving AIFL has been successful. As one of Aston University’s four research institutes, AIFL is a genuine world-leader in its field, and this award demonstrates its reputation globally. This project is a prime example of our capacities and expertise in the area of technology, and we are proud to be a partner.”


Patten is excited about the promise of AUTHOR as it is poised to make fundamental contributions to the field of NLP. “It’s really forcing us to address an issue that’s been central to natural language processing,” Patten says. “In NLP and artificial intelligence in general, we need to find a way to build hybrid systems that can incorporate both deep learning and human-interpretable representations. The field needs to find ways to make neural networks and linguistic representations work together.”


“We need to get the best of both worlds,” Patten says.


The team includes some of the world’s foremost researchers in authorship analysis, computational linguistics, and machine learning from Illinois Institute of Technology, Aston Institute for Forensic Linguistics, Rensselaer Polytechnic Institute, and Howard Brain Sciences Foundation.

You might also like...

Check out some other posts from Aston University

4 min

People still trust scientists: Aston University psychologists contribute to largest post-pandemic study on public trust

Researchers looked at trust in scientists in 68 countries and found relatively high levels of trust everywhere The TISP Many Labs study of 71,922 people included those living in under-researched nations of the Global South The majority of survey participants believe that scientists should be more involved in society and policymaking. Public trust in scientists is still high, according to a survey carried out in 68 countries by an international team of 241 researchers, led by Dr Viktoria Cologna (Harvard University, ETH Zurich) and Dr Niels Mede (University of Zurich). The study found no evidence of the oft-repeated claim of a crisis of trust in science. The team, which included Aston University School of Psychology’s Dr James Reynolds and Dr Charlotte Pennington, also found that the majority of survey participants believed that scientists should be more involved in society and policymaking. This study is the result of the Trust in Science and Science-Related Populism (TISP) Many Labs study, a collaborative effort that allowed the authors to survey 71,922 people in 68 countries, including many under-researched countries in the ‘Global South’. For the first time since the COVID-19 pandemic, the study provides global, representative survey data on the populations and regions of the world in which researchers are perceived to be most trustworthy, the extent to which they should engage with the public and whether science is prioritising important research issues. Dr Mede said: “The study is the most comprehensive post-pandemic snapshot of trust in scientists, societal expectations of their involvement in society and policymaking and public views on research priorities.” Across 68 countries, the study finds that the majority of the public has a relatively high level of trust in scientists (mean trust level = 3.62, on a scale of 1 = very low trust to 5 = very high trust). The majority of respondents also perceive scientists as qualified (78%), honest (57%) and concerned about people’s wellbeing (56%). However, the results also reveal some areas of concern. Globally, less than half of respondents (42%) believe that scientists pay attention to the views of others. Additionally, many people felt that the priorities of science are not always well-aligned with their own priorities. The researchers call upon scientists to take the results seriously and find ways to be more receptive to feedback and more open to dialogue. The findings confirm the results of previous studies that show significant differences between countries and population groups. In particular, people with right-wing political views in Western countries tend to have less trust in scientists than those with left-wing views. This suggests that attitudes toward science tend to polarise along political lines. In most countries, however, political orientation and trust in scientists were not related. A majority of respondents want science to play an active role in society and policymaking. Globally, 83% of respondents believe that scientists should communicate with the public about science, providing an impetus for increased science communication efforts. Only a minority (23%) believe that scientists should not actively advocate for specific policies. 52% believe that scientists should be more involved in the policymaking process. Participants gave high priority to research to improve public health, solve energy problems and reduce poverty. On the other hand, research to develop defence and military technology was given a lower priority. In fact, participants explicitly believe that science is prioritising the development of defence and military technology more than they would like, highlighting a potential misalignment between public and scientific priorities. Dr Cologna said: “Our results show that most people in most countries have relatively high trust in scientists and want them to play an active role in society and policymaking”. Dr Reynolds, a senior lecturer at Aston University School of Psychology, said: “This research demonstrates that people from all around the globe still have high trust in science and want scientists involved in policymaking. When we face great challenges, such as threats to public health or energy crises, the public recognise the importance that scientists can play and want us involved. This is also true of the UK where levels of public trust in science is one of the highest globally.” Dr Pennington, a senior lecturer at Aston University School of Psychology, said: “This project showcases the importance and power of big team science to answer fundamental questions about human behaviour. By pooling our expertise and resources, we were able to reach over 70,000 people and improve sample diversity and representation by recruiting from 68 countries. Overall, the study resulted in an optimistic finding – that people generally trust scientists and agree that they should engage more in society and policymaking. Such trust is important because it allows people to make research-informed decisions about their own lives.” Find out more about the research in Nature Human Behaviour by visiting https://www.nature.com/articles/s41562-024-02090-5.

4 min

Aston University-led project finds simple ways to improve the wellbeing of paediatric critical care staff

The Staff Wellbeing (SWell) project was carried out in conjunction with Birmingham Children’s Hospital and NHS England Paediatric critical care (PCC) staff experience high levels of moral distress, post-traumatic stress disorder and burnout Two simple, low-resource wellbeing sessions can be delivered by staff for staff without specialist training. The Staff Wellbeing (SWell) project, led by Aston University researchers in collaboration with Birmingham Children’s Hospital and NHS England, has developed two simple, easy-to-deliver sessions to improve the wellbeing of staff in paediatric critical care (PCC) units in UK hospitals. PCC staff are known to experience high levels of moral distress, symptoms of post-traumatic stress disorder (PTSD) and burnout, but often feel little is offered to help them with their mental health. The SWell team at Aston University, led by Professor Rachel Shaw from the Institute of Health and Neurodevelopment, realised following a literature review that there are no existing, evidence-based interventions specifically designed to improve PCC staff wellbeing. Initial work by SWell identified the ‘active ingredients’ likely to create successful intervention designs. Together with a team from NHS England, the Aston University researchers set up the SWell Collaborative Project: Interventions for Staff Wellbeing in Paediatric Critical Care, in PCC units across England and Scotland. The aim of the project was to determine the feasibility and acceptability of implementing wellbeing interventions for staff working in PCC in UK hospitals. In total, 14 of the 28 UK PCC units were involved. One hundred and four intervention sessions were run, attended by 573 individuals. Professor Shaw said: “The significance of healthcare staff wellbeing was brought to the surface during the COVID-19 pandemic, but it’s a problem that has existed far longer than that. As far as we could see researchers had focused on measuring the extent of the problem rather than coming up with possible solutions. The SWell project was initiated to understand the challenges to wellbeing when working in paediatric critical care, to determine what staff in that high-pressure environment need, and what could actually work day-to-day to make a difference. Seeing PCC staff across half the paediatric critical care units in the UK show such enthusiasm and commitment to make the SWell interventions a success has been one of the proudest experiences in my academic career to date.” The two wellbeing sessions tested are low-resource and low-intensity, and can be delivered by staff for staff without any specialist qualifications. In the session ‘Wellbeing Images’, a small group of staff is shown images representing wellbeing, with a facilitated discussion using appreciative inquiry - a way of structuring discussions to create positive change in a system or situation by focusing on what works well, rather than what is wrong. In the ‘Mad-Sad-Glad’ session, another small group reflective session, participants explore what makes them feel mad, sad and glad, and identify positive actions to resolve any issues raised. The key ingredients in both sessions are social support – providing a psychologically safe space where staff can share their sensitive experiences and emotions without judgement, providing support for each other; self-belief – boosting staff’s self-confidence and ability to identify and express their emotions in response to work; and feedback and monitoring – encouraging staff to monitor what increases their stress, when they experience challenging emotions, and what might help boost their wellbeing in those scenarios. Feedback from staff both running and participating in the SWell interventions was very positive, with high satisfaction and feasibility ratings. Participants like that the session facilitated open and honest discussions, provided opportunities to connect with colleagues and offered opportunities for generating solutions and support. One hospital staff member responsible for delivering the sessions said: “Our staff engaged really well, and it created a buzz around the unit with members of the team asking if they could be ‘swelled' on shift. A really positive experience and we are keeping it as part of our staff wellbeing package.” The team concluded that even on busy PCC units, it is feasible to deliver SWell sessions. In addition, following the sessions, staff wellbeing and depression scores improved, indicating their likely positive impact on staff. Further evaluations are needed to determine whether positive changes can be sustained over time following the SWell sessions. The work was funded by Aston University Proof of Concept Fund and NHS England. Donna Austin, an advanced critical care practitioner at University Hospital Southampton paediatric intensive care unit, said: “We were relatively new to implementing wellbeing initiatives, but we recognised the need for measures to be put in place for an improvement in staff wellbeing, as staff had described burnout, stress and poor mood. SWell has enabled our unit to become more acutely aware of the needs of the workforce and adapt what we deliver to suit the needs of the staff where possible. Staff morale and retention has been the greatest outcomes from us participating in the SWell study and ongoing SWell related interventions.” Read the paper about the SWell interventions in the journal Nursing in Critical Care at https://onlinelibrary.wiley.com/doi/10.1111/nicc.13228. For more information about SWell, visit the website.

2 min

Expert comment available - the Government's announcement for the AI Opportunities Action Plan

Expert comment is available on the the Government's announcement for the AI Opportunities Action Plan in which it is aims to roll out AI across the UK. In a speech setting out the government's plans to use AI across the UK to boost growth and deliver services more efficiently, the Prime Minister said the government had a responsibility to make AI "work for working people". The government claims that the AI Opportunities Action Plan is backed by leading tech firms, some of which have committed £14bn towards various projects, creating 13,250 jobs. It includes plans for growth zones where development will be focused, and the technology will be used to help tackle issues such as potholes. Expert comment: "The plan is a necessary step in the right direction with appropriate investment. It should be coupled with a major training programme at business and public levels to bridge the skill gap and develop essential capabilities. "It is important to specify the role that the higher education sector will play in the delivery of such a plan particularly with regards to innovation and knowledge transfer partnerships. "The government used stated that the technology will be used to help tackle issues such as potholes, however AI should be used not only in the detection of potholes, but also in their prediction. Using predictive analytics would significantly reduce the number of cameras that must be deployed to monitor road surface conditions up and down the country." Professor Abdul Hamid Sadka, Professor of Visual Media Technologies, Director, The Sir Peter Rigby Digital Futures Institute, Aston University For further details contact Nicola Jones, Head of Press & Communications (interim) on (+44) 7825 342091 or email: n.jones6@aston.ac.uk

View all posts
Powered by