New software accurately predicts personality based on tweets

**London:**In some good news for employers,researchers are developing a software that can predict a jobcandidate’s personality and behaviour by analysing theirpostings on Twitter.

People who care for the welfare of others frequently usethe words ‘we’, ‘us’, ‘friends’, ‘family’, ‘health’ and ‘home’on the micro-blogging site, according to an analysis by IBMresearch in San Jose, California.

Those who do not have those qualities are more likely touse the words ‘work’, ‘school’, ‘job’, ‘music’ and ‘beer’.Perfectionists can be identified by their use of thewords ‘perfect’ and ‘chauffeur’. People who settled for justgood enough used the words ‘mix’, ‘half’ and ‘fix’.

The researchers said 80 per cent of the results werehighly correlated with the findings of in-depth psychometricsurveys on the same 300 people who had their Twitter profilesassessed by the software, ‘The Times’ reported.

Researchers have interviewed 4,243 employees to collect450,000 pieces of data to ensure that the analysis measuresthe sort of characteristics sought by employers.

They work on the premise that five basic psychologicaltraits are needed for the right balance: extroversion, beingagreeable, conscientious and open, and having the correct dashof neuroticism.

The software scans a target’s Twitter postings to assesstheir mix.

People who are energetic and warm use longer words andmake more sexual references in their tweets; those who arealtruistic and likely to fit in with their colleagues use morefirst person plurals, more indefinite and definite articlesand swear less often, the report said.

Conscientious people discuss their achievements and uselanguage to highlight distinctions while the worriers usewords about being unwell, discuss negative emotions and talkless about topics such as family, it said.

Using shorthand such as ‘ur’ or ‘2day’ is a sign of alack of openness.

PTI