Press Coverage

In the press -

Evening Standard Britons feel positive in the morning but 16 hours later feelings turn to dread, study finds

Britain is a nation of morning people but 16 hours later feelings turn to anger and existential dread, according to a study of 800 million tweets. The study of millions of Twitter posts from cities across the country found the general mood was better earlier in the day with analytical thinking also peaking at 6am. Twitter content was sampled every hour over the course of four years across 54 of the UK’s largest cities in the research conducted by the University of Bristol.

The Daily Telegraph Study reveals our moods follow amazingly predictable daily patterns

EVER wondered why you feel miserable at 2pm, lazy at 3pm and happy at 8pm? Scientists are discovering that our moods follow amazingly predictable daily patterns. Two recent studies of more than 800 million tweets over four years discovered that people’s rising and falling moods — as revealed by the words they chose — almost exactly matched the daily patterns of two key chemicals in the body: the stress hormone cortisol and the ‘happy’ neurotransmitter serotonin.

Medium press release Study of 800-million tweets finds distinct daily cycles in our thinking patterns (Dzogang et al., 2018)

Our mode of thinking changes at different times of the day and follows a 24-hour pattern, according to new findings published in PLOS ONE. University of Bristol researchers were able to study our thinking behaviour by analysing seven-billion words used in 800-million tweets. Researchers in artificial intelligence (AI) and in medicine used AI methods to analyse aggregated and anonymised UK twitter content sampled every hour over the course of four years across 54 of the UK’s largest cities to determine if our thinking modes change collectively.

Psychology Today Time of Day Influences How Most People Think (and Tweet)

A massive analysis of 800 million anonymous tweets — containing over seven billion words — reveals universal trends in how modes of thinking tend to fluctuate over the course of each daily 24-hour cycle. This paper, “Diurnal Variations of Psychometric Indicators in Twitter Content,” was published June 20 in the journal PLOS ONE. For this pioneering study, researchers from the University of Bristol used artificial intelligence (AI) to track specific word usage on Twitter from a large population sample during multiple 24-hour circadian cycles over a four-year period. Tweets sent during big holidays were excluded, because the language used during Christmas, New Year's, Valentine's Day, etc., was skewed by the nature of each particular holiday.

Voice of America Negative Sentiments Follow Seasonal Patterns

Studying statistics of sentiments expressed by large numbers of people on Twitter, as well as how many times certain pages of the online encyclopedia Wikipedia were visited, researchers found that negative feelings were more prominent in winter, especially in November. Anxiety and anger are expressed more between September and April than during other periods of the year. The number of visits to pages describing panic disorder peaks in April.

Forbes Big Data Social Media Study Reveals Our Cognitive-Emotional Patterns

A big data study probing seven billion words in 800 million tweets, spanning over four years and 54 cities reveals our shared patterns of thinking and feeling throughout the course of each day. The findings may indicate the emergence of a cognitive-emotional circadian rhythm. A new PLOS ONE study published today, shows we’re at the height of our logical, analytical faculties at 6 am. This also appears to be the time of day we’re most concerned about power and success. By nightfall, we tend to become a lot more impulsive, social and emotional. Between 3 am and 4 am we hit peak existential mode. Words associated with death peak at around midnight and arc into words associated with religion just before sunrise. Indicators for negative emotion peak in the evenin

The Times Morning Glory

The sun is up and humans up with it have a bounce in their step. Early in the day, we are analytical, full of vim, positive and focused. Later, as the sun sinks below the yard-arm, happy campers turn into sweary angst-ridden grumps. That’s official: artificial intelligence researchers at Bristol University have crunched the numbers, and more specifically the words, from 800 million tweets from 54 cities across Britain over the past four years. Their algorithm does not examine the content itself but assesses words according to their tone; upbeat or down.

Itv Analytical thinking peaks at 6am, according to study of 800 million tweets

A study of 800 million tweets has found that analytical thinking peaks at 6am – with people changing to a more emotional and existential tone in the evening. The research, by the University of Bristol and published in the journal PLOS ONE, involved the analysis of seven billion words used in 800 million tweets. Twitter content was sampled every hour over the course of four years across 54 of the UK’s largest cities to determine whether thinking modes change collectively.

Motherboard Study of 800 Million Tweets Shows We Get Really Emo Late at Night

University of Bristol researchers found patterns around what we say online. What we tweet might be dictated by time of day and our own circadian rhythms, according to a new study of 800 million tweets. University of Bristol researchers studied seven billion words sent from across 54 of the UK's largest cities over four years—between January 2010 and November 2014—to determine patterns in how we think and feel throughout the day. They scraped tweets from the Twitter search API, anonymized the data, and used 73 psychometric indicators to tease out the mood and emotion behind the tweets.

Medical News Today How social media reflects our daily mood changes

Researchers from the University of Bristol in the United Kingdom have used a dataset of more than 800 million Twitter messages to evaluate how collective mood changes over the course of 24 hours and across the seasons.
expressions ranging from angry to happy Researchers show that social media can determine mood changes between weekdays and weekends, as well as across the seasons. The most extensive study of its kind to date was led by machine learning researcher Dr. Fabon Dzogang. He conducted the research with neuroscientist Prof. Stafford Lightman and Nello Cristianini, a professor of artificial intelligence from the Department of Engineering Mathematics.

Wired Twitter users are analytical in the morning, angsty at night.

Their findings reflect not just variations in mood, but styles of thought. Analytical thinking—which correlates with frequent use of nouns, articles, and prepositions—seems to peak early in the day, along with an increased concern with things like power and achievement. Late at night, however, existential thinking dominates. By 3:00 am, positive emotions are at their lowest, and topics like death and religion have peaked. At the population level, anyway. Well, the British population level.

Daily Mail How science holds the answers to a successful 2019: Get rich in February, find love in October, make friends in July... the calendar you need for the best year yet

It feels like it should be an optimistic month, with the days getting longer and summer on the horizon, but once again science confounds us. According to a study of eight million Tweets over four years in the UK, anxiety peaks in April — and it's also when we're buying the most over-the counter stress remedies. 'One hypothesis is that spring is a time when the rate of change in the levels of sunlight is at its fastest; perhaps it's so fast it is interfering with our circadian rhythms and causing anxiety,' says study leader, Dr Fabon Dzogang at Bristol University.