Twitter Success Thrives on Narrow Focus
Those looking to build a substantial following on Twitter would do well to stick to one particular topic, rather than use Twitter to discuss a wide range of subjects, a Carnegie Mellon University researcher has advised.
Twitter accounts that stay focused on a particular topic garner more followers than those that cover a wider variety of topics, according to a study conducted by Carnegie Mellon Language Technologies Institute researcher Yi-Chia Wang.
Yi-Chia discussed her findings at the Association for Computing Machinery's Conference on Human Factors in Computing Systems, being held this week in Austin, Texas.
With Twitter becoming a popular promotional platform for both organizations and individuals, work such as Yi-Chia's could help users get the most from their involvement with the service. At last count, Twitter had more 140 million users. Not everyone uses it effectively however -- 25 percent of Twitter users have no followers at all, Yi-Chia said.
By keeping focused to a single topic, a Twitter user can attract other people who are also interested in that topic. Those people may then connect with one another, to generate further discussion and build a community around the topic, Yi-Chia said.
This line of thinking might go against the conventional wisdom of discussing as many topics as possible in order to attract a broader audience, a common practice with other forms of media. "Diverse topics can potentially appeal to more people. A political blog may [cover] a wide range of potential topics -- such as foreign policy, economy or the presidential election -- so it may appeal to people who care about any of these topics," she said.
Such thinking doesn't hold up on Twitter though, at least in Yi-Chia's study. A narrower focus, "although potentially would attract fewer people" would also attract people with similar interests, ones who would "more easily identify themselves with the [Twitter account] and better anticipate what they can get" from subscribing, she suggested.
In her study, Yi-Chia studied how 480 active Twitter users fared in their first year of service. On average, these users posted 1,574 messages.
Success was defined by two factors. One factor was how many followers a user attracted. But Yi-Chia also looked at social tie density, or the degree to which followers also subscribed to fellow followers. Social tie density is a good indicator of the size of a community around a Twitter user.
To determine how closely a Twitter user kept to a single topic, Yi-Chia used a statistical method called average pairwise cosine similarity, or AvgCosSim, which measures the degree to which multiple sets of text, such as groups of Twitter messages, share common words. When people talk about a single topic, they tend to use the same words, Yi-Chia explained. U.S. conservatives discussing the topic of health care, for instance, frequently use words such as "Obama," "Obamacare," "socialism," and "repeal" for instance. The higher the AvgCosSim score, the more likely the Twitter messages being analyzed were on a single topic.
In her analysis, Yi-Chia found that Twitters users with higher AvgCosSim scores had more followers than those with lower scores. "Topic focus is significantly correlated with membership size," Yi-Chia said. In other words, Twitter users who stuck to a single topic gathered more followers and created a more vibrant community than those who touched upon multiple topics. For instance, increasing the AvgCosSim score by 0.01 (in effect moving from the 25th to the 50th percentile) on average attracted 111 more followers.
The audience in attendance praised the work, noting that it pointed to future areas of research. Someone noted that some Twitter accounts reaped many followers not by staying on one topic, but by some other means, such as offering only humorous Twitter messages. Yi-Chia admitted that the study does not take into account such types of Twitter accounts, though the study did factor out celebrities, such as Ashton Kutcher, who gain large followings through name recognition.