Recently, I mentioned a software that detects depression in text without obvious terms like “depression” or “suicide”. It seems mapping the mental health or emotional status of the online world is becoming a reality and here is a new evidence for that. The New Scientist reported a study in which scientists used the positive and negative words of Twitter messages in order to map the country’s emotional state:
To glean mood from the 140-character-long messages, the researchers analysed all public tweets posted between September 2006 and August 2009. They filtered them to find tweets that contain words included in a psychological word-rating system called Affective Norms for English Words – a low-scoring word on ANEW is considered negative, a high-scoring one positive. They also filtered out tweets from users outside the US, and also from those in the US who did not include their exact location – for example, their city – in their Twitter profile.
That left 300 million tweets, each of which was awarded a mood score based on the number of positive or negative words it contained. For example, “diamond”, “love” and “paradise” indicate happiness, whereas “funeral”, “rape” and “suicide” are negative. “Dentist” is fairly neutral.