Skip to content
Search

Latest Stories

Researchers use Twitter data and AI to create predictive model for mental disorders

The researchers’ preliminary findings suggest that a person’s social media friends and followers could indicate the likelihood of them developing depression

Researchers use Twitter data and AI to create predictive model for mental disorders

Researchers at the University of São Paulo are working on developing prediction models for anxiety and depression using Twitter and artificial intelligence (AI). The models aim to detect signs of these mental illnesses before clinical diagnosis.

The researchers' preliminary findings suggest that a person's social media friends and followers could indicate the likelihood of them developing depression.


The study involved constructing a database called SetembroBR, which included a corpus of 47 million publicly posted Portuguese texts and a network of connections between 3,900 Twitter users.

The research is published in the Language Resources and Evaluation journal.

During the Covid-19 pandemic, researchers manually collected timelines of tweets from about 19,000 users who had reportedly been diagnosed with or treated for mental health problems before the survey.

The study used two datasets, one for users with mental health diagnoses and another for control purposes, selected at random to distinguish between people with depression and the general population.

Ivandre Paraboni, a professor at USP and the last author of the study, explained that this was the first step in creating the anxiety and depression prediction model.

The study collected tweets from friends and followers of people with mental health problems, as they tend to follow certain accounts related to mental health.

Deep learning was used to create text classifiers and word embeddings based on bidirectional encoder representations from transformers (BERT), a machine learning algorithm employed for natural language processing (NLP) to detect the likelihood of a person developing depression based on their social media connections. The findings are still in progress.

Researchers found that BERT was the best model in predicting depression and anxiety by monitoring sequential data relationships such as words in a sentence.

People with depression tended to write about themselves and use topics such as death, crisis, and psychology.

Also, according to Paraboni, the signs of depression on social media may differ from those observed during a doctor's visit.

For example, the study found that depressed users often used the first-person singular pronouns "I" and "me" and the heart emoji, which could be considered a symbol of affection and love. These observations could potentially be used as indicators of depression.

"This is widely felt to be a symbol of affection and love, but maybe psychologists haven't yet characterised it as such," Paraboni said.

The researchers are now working on expanding the database, improving their computational methods and enhancing the models to develop a screening tool for identifying individuals at risk of mental health issues.

The tool may also assist families and friends in detecting depression and anxiety in young people.

(With inputs from PTI)

More For You

menstruation

The findings come from a UK survey of more than 12,000 women

iStock

Heavier bleeding and iron loss linked to long Covid in women, study finds

Highlights:

  • Survey of more than 12,000 UK women finds heavier, longer periods linked to long Covid
  • Symptom severity rises and falls across the menstrual cycle, worsening during periods
  • Tests reveal inflammation in womb lining and hormonal changes, but no damage to ovaries
  • Iron deficiency risk may exacerbate fatigue, dizziness and other common long Covid symptoms

Study highlights link between long Covid and menstrual changes

Women with long Covid are more likely to experience longer and heavier periods, putting them at increased risk of iron deficiency, researchers have found. The findings come from a UK survey of more than 12,000 women, which also showed that the severity of long Covid symptoms fluctuated across the menstrual cycle and often worsened during menstruation.

Findings from UK survey

Between March and May 2021, 12,187 women completed an online survey. Of these, more than 1,000 had long Covid, over 1,700 had recovered from the virus, and 9,400 had never tested positive. The study revealed that women with long Covid reported heavier and longer periods, as well as more frequent bleeding between cycles, compared with other groups.

Keep ReadingShow less
World Curry Festival 2025

The discovery coincides with Bradford’s City of Culture celebrations

World Curry Festival

Bradford’s first curry house traced back to 1942 ahead of World Curry Festival

Highlights:

  • Research for the World Curry Festival uncovered evidence of a curry house in Bradford in 1942.
  • Cafe Nasim, later called The Bengal Restaurant, is thought to be the city’s first.
  • The discovery coincides with Bradford’s City of Culture celebrations.
  • Festival events will include theatre, lectures, and a street food market.

Historic discovery in Bradford’s food heritage

Bradford’s claim as the curry capital of Britain has gained new historical depth. Organisers of the World Curry Festival have uncovered evidence that the city’s first curry house opened in 1942.

Documents revealed that Cafe Nasim, later renamed The Bengal Restaurant, once stood on the site of the current Kashmir Restaurant on Morley Street. Researcher David Pendleton identified an advert for the cafe in the Yorkshire Observer dated December 1942, describing it as “Bradford’s First Indian Restaurant”.

Keep ReadingShow less
​Dilemmas of dating in a digital world

We are living faster than ever before

AMG

​Dilemmas of dating in a digital world

Shiveena Haque

Finding romance today feels like trying to align stars in a night sky that refuses to stay still

When was the last time you stumbled into a conversation that made your heart skip? Or exchanged a sweet beginning to a love story - organically, without the buffer of screens, swipes, or curated profiles? In 2025, those moments feel rarer, swallowed up by the quickening pace of life.

Keep ReadingShow less
sugary drinks and ice cream

Researchers from the UK and US analysed data from American households between 2004 and 2019

iStock

Global warming may drive higher consumption of sugary drinks and ice cream, study warns

Highlights:

  • Hotter days linked to greater intake of sugary drinks and frozen desserts
  • Lower-income households most affected, research finds
  • Climate change could worsen health risks linked to sugar consumption
  • Study based on 15 years of US household food purchasing data

Sugary consumption rising with heat

People are more likely to consume sugary drinks and ice cream on warmer days, particularly in lower-income households, according to new research. The study warns that climate change could intensify this trend, adding to health risks as global temperatures continue to rise.

Sugar consumption is a major contributor to obesity, diabetes, and cardiovascular disease, and has surged worldwide in recent decades. The findings, published in Nature Climate Change, suggest that rising heat could be nudging more people towards high-sugar products such as soda, juice and ice cream.

Keep ReadingShow less
Camellia Panjabi's cookbook elevates
vegetables from sides to stars

Camellia Panjabi (Photo: Ursula Sierek)

Camellia Panjabi's cookbook elevates vegetables from sides to stars

RESTAURATEUR and writer Camellia Panjabi puts the spotlight on vegetables in her new book, as she said they were never given the status of a “hero” in the way fish, chicken or prawns are.

Panjabi’s Vegetables: The Indian Way features more than 120 recipes, with notes on nutrition, Ayurvedic insights and cooking methods that support digestion.

Keep ReadingShow less