Analyzing Linguistic Differences between Owner and Staff Attributed Tweets

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2848–2853 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 2848 Analyzing Linguistic Differences between Owner and Staff Attributed Tweets Daniel Preot¸iuc-Pietro Bloomberg LP dpreotiucpie@bloomberg.net Rita Devlin Marier Bloomberg LP rdevlin5@bloomberg.net Abstract Research on social media has to date assumed that all posts from an account are authored by the same person. In this study, we challenge this assumption and study the linguistic dif- ferences between posts signed by the account owner or attributed to their staff. We introduce a novel data set of tweets posted by U.S. politi- cians who self-reported their tweets using a signature. We analyze the linguistic topics and style features that distinguish the two types of tweets. Predictive results show that we are able to distinguish between owner and staff at- tributed tweets with good accuracy, even when not using any training data from that account. 1 Introduction Social media has become one of the main venues for breaking news that come directly from primary sources. Platforms such as Twitter have started to play a key role in elections (Politico, 2017) and have become widely used by public figures to dis- seminate their activities and opinions. However, posts are rarely authored by the public figure who owns the account; rather, they are posted by staff who update followers on the thoughts, stances and activities of the owner. This study introduces a new application of Nat- ural Language Processing: predicting which posts from a Twitter account are authored by the owner of an account. Direct applications include predict- ing owner authored tweets for unseen users and can be useful to political or PR advisers to gain a better understanding on how to craft more per- sonal or engaging messages. Past research has experimented with predicting user types or traits from tweets (Pennacchiotti and Popescu, 2011; McCorriston et al., 2015). How- ever, all these studies have relied on the assump- tion that tweets posted from an account were all written by the same person. No previous study has Figure 1: Example of a politician account where signed tweets are attributed to the account owner. looked at predicting which tweets from the same Twitter account were authored by different per- sons, here staffers or the owner of the Twitter ac- count. Figure 1 shows an example of a U.S. politi- cian who signs their tweets by adding ‘-PM’ at the end of the tweet. Staff posts are likely to be different in terms of topics, style, timing or impact to posts attributed to the owner of the account. The goal of the present study is thus to: • analyze linguistic differences between the two types of tweets in terms of words, topics, style, type and impact; • build a model that predicts if a tweet is at- tributed to the account owner or their staff. To this end, we introduce a novel data set con- sisting of over 200,000 tweets from …

Content truncated to 500 words