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

3 min

Aston University’s Professor Ian Maidment receives prestigious National Institute for Health and Care Research award

Professor Ian Maidment has received a National Institute for Health and Care Research (NIHR) Senior Investigator Award The award recognises his outstanding leadership contributions to the work of the NIHR and his excellent track record of securing NIHR funding Professor Maidment is the first academic at Aston University to receive the honour. Professor Ian Maidment at Aston Pharmacy School has received a prestigious Senior Investigator Award from the National Institute for Health and Care Research (NIHR). The NIHR gives the award to researchers in recognition of outstanding leadership contributions to the work of the NIHR and an excellent track record of securing NIHR funding. As a senior investigator, Professor Maidment will act as an ambassador for NIHR, and help to guide strategy and tackle challenges in the health and social care landscape. He will join the NIHR College of around 200 senior investigators. Professor Maidment is the first academic at Aston University to receive the award and one of few pharmacists in the UK to receive such an award. Professor Maidment joined Aston University in 2012 as a senior lecturer, which marked his first step into academia after more than 20 years working in the NHS, both as a pharmacist and leading R&D. During his time in the NHS, he published 40 papers in peer-reviewed journals. These formed the basis of a PhD by previous publication, and Professor Maidment was the first person to obtain a PhD at Aston University by this route. He was promoted to reader in 2018 and a full chair in 2022. Professor Maidment specialises in the health care of older people and those with mental health conditions, and the use of medication to treat them. This includes projects investigating the long-standing and international healthcare priority of managing anti-psychotic weight gain. From this research project, guidance will be developed both for patients and practitioners. His research with older people has identified the need to focus on reducing medication burden and investigating the link between some medications and dementia. He also studies how to best use the expertise of community pharmacy to improve outcomes, for example in COVID vaccination and more recently how to make independent prescribing by community pharmacy work better; the importance of this issue was identified by UK Prime Minister Keir Starmer. The award also recognises Professor Maidment’s strong links with the NIHR and critically his continued role in supporting its work. This includes mentoring other researchers, leadership and contributing to the development of the NIHR. Professor Maidment said: “Optimising medication in the real world is a key research priority; about half of all people struggle with adherence to medication. Much of my research has been focused on bringing the patient voice to key research questions. If we can fully understand the patient and family carer view, then we can start to get the medication right.” Professor Anthony Hilton, Aston University pro-vice-chancellor and executive dean of the College of Health and Life Sciences, said: “Professor Ian Maidment’s NIHR Senior Investigator Award is a well-deserved recognition of his exceptional research in medication safety and the care of older adults and people with severe mental illness, such as schizophrenia. His work has not only advanced academic understanding but has also shaped real-world healthcare practices, improving outcomes for patients. “This achievement reflects his dedication, expertise and commitment to impactful research and his outstanding leadership contributions to the work of the NIHR. At Aston University, we are delighted to celebrate Ian’s success and the significant contribution he continues to make to the field.”

4 min

Aston University study reveals the illusion of ‘dazzle’ paint on World War I battleships

The Zealandia in wartime dazzle paint. Image: Australian National Maritime Museum on The Commons Geometric ‘dazzle’ camouflage was used on ships in WWI to confuse enemy onlookers as to the direction and speed of the ship Timothy Meese and Samantha Strong reanalysed historic data from 1919 and found that the ‘horizon effect’ is more effective for confusion When viewing a ship at distance, it often appears to be travelling along the horizon, regardless of its actual direction of travel – this is the ‘horizon effect’. A new analysis of 105-year-old data on the effectiveness of ‘dazzle’ camouflage on battleships in World War I by Aston University researchers Professor Tim Meese and Dr Samantha Strong has found that while dazzle had some effect, the ‘horizon effect’ had far more influence when it came to confusing the enemy. During World War I, navies experimented with painting ships with ‘dazzle’ camouflage – geometric shapes and stripes – in an attempt to confuse U-boat captains as to the speed and direction of travel of the ships and make them harder to attack. The separate ‘horizon effect’ is when a person looks at a ship in the distance, and it appears to be travelling along the horizon, regardless of its actual direction of travel. Ships travelling at an angle of up to 25° relative to the horizon appear to be travelling directly along it. Even with those at a greater angle to the horizon, onlookers significantly underestimate the angle. Despite widespread use of dazzle camouflage, it was not until 1919 that a proper, quantitative study was carried out, by MIT naval architecture and marine engineering student Leo Blodgett for his degree thesis. He painted model ships in dazzle patterns and placed them in a mechanical test theatre with a periscope, like those used by U-boat captains, to measure how much onlookers’ estimations of the ships’ direction of travel deviated from their actual direction of travel. Professor Meese and Dr Strong realised that while the data collected by Blodgett was useful, his methods of experimental design fell short of modern standards. He’d found that dazzle camouflage worked, but the Aston University team suspected that dazzle alone was not responsible for the results seen, cleaned the data and designed new analysis to better understand what it really shows. Dr Strong, a senior lecturer at Aston University’s School of Optometry, said: “It's necessary to have a control condition to draw firm conclusions, and Blodgett's report of his own control was too vague to be useful. We ran our own version of the experiment using photographs from his thesis and compared the results across the original dazzle camouflage versions and versions with the camouflage edited out. Our experiment worked well. Both types of ships produced the horizon effect, but the dazzle imposed an additional twist.” If the errors made by the onlookers in the perceived direction of travel of the ship were entirely due to the ‘twist’ on perspective caused by dazzle paintwork, the bow, or front, of the ship, would always be seen to twist away from its true direction. However, Professor Meese and Dr Strong instead showed that when the true direction was pointing away from the observer, the bow was often perceived to twist towards the observer instead. Their detailed analysis showed a small effect of twist from the dazzle camouflage but a much larger one from the horizon effect. Sometimes these effects were in competition, sometimes in harmony. Professor Meese, a professor of vision science at the School of Optometry, said: “We knew already about the twist and horizon effects from contemporary computer-based work with colleagues at Abertay University. The remarkable finding here is that these same two effects, in similar proportions, are clearly evident in participants familiar with the art of camouflage deception, including a lieutenant in a European navy. This adds considerable credibility to our earlier conclusions by showing that the horizon effect – which has nothing to do with dazzle – was not overcome by those best placed to know better. “This is a clear case where visual perception is more powerful than knowledge. In fact, back in the dazzle days, the horizon effect was not identified at all, and Blodgett's measurements of perceptual bias were attributed entirely to the camouflage, deceiving the deceivers.” Professor Meese and Dr Strong say that more work is required to fully understand how dazzle might have increased perceptual uncertainty of direction and speed but also the geometry behind torpedo-aiming tactics that might have supported some countermeasures. Visit https://doi.org/10.1177/20416695241312316 to read the full paper in i-Perception.

1 min

Lab grown meat could be on sale in UK within two years - but what is lab-grown meat?

Meat, dairy and sugar grown in a lab could be on sale in the UK for human consumption for the first time within two years, sooner than expected. The Food Standards Agency (FSA) is looking at how it can speed up the approval process for lab-grown foods. Such products are grown from cells in small chemical plants. UK firms have led the way in the field scientifically but feel they have been held back by the current regulations. Aston University has been working on cultivated meat - find out more about what lab-made meat is  made of and how it is created in the podcast Breaking Down Barriers on Spotify   https://open.spotify.com/episode/7bFy1gr2LJCwiRLPAT9Hml For further details contact Nicola Jones, Press and Communications Manager, on (+44) 7825 342091 or email: n.jones6@aston.ac.uk

View all posts
Powered by