Home
News
Videos
Podcasts
Menu
Акционерное общество "ТВ БРИКС"
tvbrics@tvbrics.com
Рубцов переулок, д.13, Москва, 105082, RU
+74996425304
Currencies:
RUB/USD 0,0119
BRL/USD 0,1935
0,003
INR/USD 0,0104
CNY/USD 0,149
0,0004
ZAR/USD 0,0613
0,0003
IDR/USD 0,0001
SPACE FOR MEDIA DIPLOMACY
19:30 «BRICSdialogue»
19:30 «BRICSdialogue»
Now 16+
19:30

«BRICSdialogue»

It is indicated Moscow time in the programme. Please take into account the time difference with your time zone.
20:00 «Russian Lessons with Tanya Semke»
Next
20:00

«Russian Lessons with Tanya Semke»

16+
20:15

«Laboratorium»

16+
20:30

«Lеt's be clear»

16+
Menu
Broadcast «BRICSdialogue»
RUB/USD
0,0119
BRL/USD
0,1935
0,003
INR/USD
0,0104
CNY/USD
0,149
0,0004
ZAR/USD
0,0613
0,0003
IDR/USD
0,0001
TV BRICS Apps

SPbU scientists test how accurately AI can create psychological profile of person

Researchers found that models tend to attribute more positive characteristics to people than indicated by the results of psychological tests

Scientists from St. Petersburg State University (SPbU), a TV BRICS partner, together with specialists from the Artificial Intelligence Research Institute (AIRI) and the Institute of Psychology of the Russian Academy of Sciences, have tested how accurately modern language models can predict a person's psychological characteristics based on a standard interview. This was reported on the SPbU website.

The study involved 645 people. Each participant answered interview questions and completed psychological tests assessing 38 indicators, including personality traits, values, moral and social attitudes, as well as views on material possessions.

The scientists then provided the interview materials to five language models. The neural networks were tasked with predicting how a specific participant would answer the psychological test questions. The predictions were then compared with the actual responses of the participants.

The researchers found that AI is better at predicting psychological characteristics that are more clearly reflected in speech and self-description. For example, the models identified extraversion with relatively high accuracy.

AI generally tends to view people in a more positive light: it overestimated assessments of kindness and honesty and underestimated indicators of narcissism, Machiavellianism and psychopathy.

Neural networks found it more difficult to determine levels of anxiety, the pursuit of pleasure and a person's views on fairness.

“In an applied context, such technologies can be used for personalised learning, psychological and motivational support, organisational communications and human interaction with intelligent systems. A separate promising area is modelling the behaviour not only of individuals but also of entire teams,” said SPbU Research Fellow Anastasia Panfilova.

The work continues SPbU’s research focus on studying the capabilities of large language models in analysing human behaviour.