NLP for social media

Now we will discuss how NLP has influenced social media mining. Here we will discuss findings presented in several papers. These findings include detecting rumors from truth and detecting emotions and identifying manipulations of words by politicians, for example, to gain more support (that is, political framing).

Detecting rumors in social media

In Detect Rumors Using Time Series of Social Context Information on Microblogging Websites [20], Jing Ma and others propose a way to detect rumors in microblogs. Rumors are stories or statements that are either deliberately false or for which the truth is not verified. Identifying rumors in their early phases is important to prevent false/invalid information being delivered to people. In this paper, an event is defined as a set of microblogs relevant to that event. A time-sensitive context feature is derived for each microblog and they are binned into time intervals depending on the time the microblog appeared. Thereafter, they...