
Russian Scientists Teach AI to Analyse Emotions of Participants at Online Events
HSE researchers have proposed a new neural network method for recognising emotions and people's engagement. The algorithms are based on the analysis of video images of faces and significantly outperform existing single models. The developed models are suitable for low-performance equipment, including mobile devices. The results can be implemented into video conferencing tools and online learning systems to analyse the engagement and emotions of participants. The results of the study were published in IEEE Transactions on Affective Computing.

In Assessing Motivation, Rating Scales Are Far from the Best Choice
Researchers from HSE University and the Pushkin Institute have demonstrated that pairwise comparisons work better than rating scales for measuring motivation. The reason is that many people cannot rank their motives in a hierarchical fashion. The study findings are published in Frontiers in Psychology.

Brain Found to Simultaneously Process Linguistic and Extralinguistic Information
An international team of scientists from the UK, Spain, Denmark and Russia (including researchers from the HSE Institute for Cognitive Neuroscience) conducted an experiment demonstrating that people automatically integrate extralinguistic information into grammatical processing during verbal communication. The study findings were published in the Scientific Reports Journal.

AI Worse at Recognizing Images than Humans
Researchers from HSE University and Moscow Polytechnic University have discovered that AI models are unable to represent features of human vision due to a lack of tight coupling with the respective physiology, so they are worse at recognizing images. The results of the study were published in the Proceedings of the Seventh International Congress on Information and Communication Technology.

Machine Learning Helps Improve Perovskite Solar Cells
A team of researchers from HSE MIEM, LPI RAS, and the University of Southern California have applied machine learning to the analysis of internal defects in perovskite solar cells and proposed ways to improve their energy efficiency. The findings of the study performed on the Cs2AgBiBr6 double perovskite can be used to develop more efficient and durable perovskite-based materials. The paper has been published in the Journal of Physical Chemistry Letters.

Russian Researchers Propose New Approach to Studying Facial Emotion Recognition
Researchers of the HSE University and the Southern Federal University (SFedU) have tested a new method for studying the perception of facial emotional expressions. They suggest that asking subjects to recognise emotional expressions from dynamic video clips rather than static photographs can improve the accuracy of findings, eg in psychiatric and neurological studies. The paper is published in Applied Sciences.

Scientists Learn to Better Predict Space Weather
An international team of astrophysicists has been studying the formation of strong electrostatic waves, ion holes, in the Earth's magnetotail and assessing their impact on space weather. They found that ion holes propagate oblique to the local magnetic field. The study's findings can contribute to a better understanding of processes in the Earth's magnetotail which affect space weather in the near-Earth plasma environment and the polar region. The paper is published in Geophysical Research Letters.

Russians Feel Disappointed with Their Income if Their Reference Group Average is Higher
Researcher Anastasia Dubnovitskaya of HSE University has studied the impact of social comparison on the level of Russians' pay satisfaction. The study used data from the Russia Longitudinal Monitoring Survey — HSE University (RLMS-HSE) from 2002 to 2018. It turned out that the main contribution to Russians' pay satisfaction is the difference between their actual pay and the average wages of the reference group — people with similar characteristics. The size of one's own wages was of secondary importance.

AI Helps Discover New Space Anomalies
The SNAD team, an international network of researchers including Matvey Kornilov, Associate Professor of the HSE University Faculty of Physics, has discovered 11 previously undetected space anomalies, seven of which are supernova candidates. The researchers analysed digital images of the Northern sky taken in 2018 using a k-D tree to detect anomalies through the ‘nearest neighbour’ method. Machine learning algorithms helped automate the search. The paper is published in New Astronomy.

New RSCI List Includes 944 Journals
The Russian Science Citation Index (RSCI) quality assessment and journal selection working group has updated its list of journals based on the results of expert review and monitoring of the quality of publications. The expert review examined such criteria as the scientific level of the journal, its relevance, its consistency, the level of the scientists on its editorial board, the journal’s adherence to publishing and scientific ethics, and the quality of its formatting.