Cornell researchers say a combination of language, positive and negative words and even asking people to retweet help.

They say the results of the study, which was partly funded by Google, could not only improve your twitter performance, but also improve your chances in business meetings.

 'You want to say something about it to make people look at it,' said Lillian Lee, who read the research. 

The results might even be applied to longer forms of discourse, from essays to getting your idea accepted in a committee meeting. 

'We're looking at persuasion everywhere,' said Lee, professor of computer science and information science.

The team reported their results in the June issue of the Proceedings of the Association for Computational Linguistics. 

Using automated text analysis, Cornell researchers identified an array of features that can make a message more likely to get attention.

They tested their ideas on Twitter, where their computer algorithm predicted more accurately than human observers which version of a tweet would be retweeted more.  

The researchers collected and compared thousands of these pairs, and after taking into account the effect of repetition, the experiment showed that wording still matters. 

On Twitter, many posts are links to websites the poster thinks are important. 

The Cornell researchers tested each one separately, then combined them into their algorithm.

The computer looks for the occurrence of certain keywords and compares 'bigrams' – combinations of two words. 

Such combinations may reflect a linguistic style. 'Cornell,' for example, might often be followed by 'Chronicle' within the campus community, but on Twitter you might find 'Cornell research,' 'Cornell students,' 'Cornell ornithologists.' 

'We would love to capture amusingness or cleverness, but we haven't found a way to do that yet,' Lee added.

Meanwhile, the researchers have created a website where you can see what the algorithm thinks of your own tweets. 

The researchers conclude with a challenge: Social scientists should try to find out why these tactics work. 

The research was supported by the National Science Foundation and Google. 

(dailymail.co.uk)