PeerJ Computer Science, Human Impact Collection: Interview with Nikos Aletras, co-author of one of the journal’s most highly cited papers

 

Gerd Altmann from Pixabay

In our latest PeerJ Computer Science Collection we highlight computer science research that interacts with and affects human existence – impacting health, behaviour and activity. The Collection includes “Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective,” one of the journal’s most highly cited papers. We asked co-author Nikos Aletras a few questions about the papers and its legacy.

Nikos Aletras

Hi Nikos. Thanks for agreeing to answer some questions for us. Can you tell us a bit about yourself?

I’m a Lecturer (equivalent of Assistant Professor) in Natural Language Processing (NLP) in the Computer Science Department, co-affiliated with the Machine Learning (ML) group at University of Sheffield. My research interests include social media analysis, NLP in the legal domain and methods for understanding large document collections.  I’ve gained industrial experience working as a scientist at Amazon (Amazon Research Cambridge and Alexa) and I was a research associate at UCL, Department of Computer Science, Media Futures Group.

Can you briefly explain the research you published in PeerJ Computer Science?

This is the first paper to use NLP techniques to predict judicial outcomes. Given the factual descriptions of legal cases, we train text classification algorithms that can predict for a new case whether there is a violation of an article of the European Convention of Human Rights.

Can you tell us anything about how your research has been applied and re-used since its publication?

It led to a follow-up paper (Chalkidis et al., ACL 2019) and the organisation of the Natural Legal Language Processing workshop. Our research also sparked an interest in the law community on how technology can be used to improve access to justice. It has received worldwide media coverage and was mentioned by the British Supreme Court President, and The Guardian.

What persuaded you to publish with PeerJ Computer Science when it was still a relatively unknown quantity?

PeerJ Computer Science is an open journal that supports multidisciplinary research which fitted well with the scope of our paper.

How would you describe your experience of PeerJ?

Very fast turnaround, extremely high-quality review process. I also like the fact that reviews can also be made publicly available for better scrutiny.

—————————-

Other papers in the Computer Science, Human Impacts Collection include:

Supervised deep learning embeddings for the prediction of cervical cancer diagnosis

Diagnosis of cervical cancer often requires frequent and very time-consuming clinical exams. In this context, machine learning can provide effective tools to speed up the diagnosis process, by processing high-scale patients’ datasets in a few minutes.

In this manuscript, Fernandes and colleagues present a computational system for the prediction of cervical patient diagnosis, and for the interpretation of its results. Their system consists of a loss function that allows joint optimization of dimensionality reduction, and classification techniques able to promote relevant properties in the embedded spaces. Deep learning methods predict the diagnosis of the patients with high accuracy, and their application to other datasets showed that their robustness and effectiveness is not bounded to cervical cancer.

Machine learning with remote sensing data to locate uncontacted indigenous villages in Amazonia

Key to the survival of uncontacted indigenous Amazonian societies is being able to locate and track small, isolated and semi-nomadic populations. Walker & Hamilton use a non-invasive methodology to track isolated indigenous populations, employing remote sensing technology with Landsat satellite sensors. They use machine learning techniques applied to remote sensing data to differentiate between contacted and uncontacted indigenous populations.

The importance of behavioral data to identify online fake reviews for tourism businesses: a systematic review

As the use and importance of online reviews has grown, so have the number of fake reviews, especially in the tourism industry. In this systematic review, Reyez-Menendez and colleagues aim to thoroughly investigate the phenomenon of fake online reviews in the tourism sector on social networking and online reviews sites, and provide helpful strategies to counteract the ubiquity of fake reviews for tourism businesses.

Adaptive automation: automatically (dis)engaging automation during visually distracted driving

Automated driving is often proposed as a solution to human errors. Christopher D.D. Cabrall and colleagues focused on adaptively allocating steering control either to the driver or to an automated pilot based on momentary driver distraction measured from an eye tracker. Their research showed that a system where automation is engaged only when the driver is measured to be distracted has the potential to increase safety when compared to manual driving.

Read these and other papers in our Computer Science, Human Impacts Collection here

PeerJ Computer Science welcomes submissions of computer science research with human impacts.

You can find more PeerJ author interviews here.

You may also like...