Uncertainty Identification in Microblogs

Abstract

Microblogging, like Twitter, has become a popular platform of human expressions, through which users can easily produce content on breaking news, public events, or products. The massive amount of microblogging data is a useful and timely source that carries mass sentiments, beliefs and opinions on various topics. Users express themselves freely with varying levels of uncertainty, which makes exploiting microblogs as a source of data a tedious task requiring this aspect to be taken into consideration. Here we talk about the uncertainty expressed in microblogs not the uncertainty relative to the claimed information factuality. This aspect that we approach has received little attention in the context of microblogging, whereas it is important to know with which degree of uncertainty the users intend to provide information. The research works carrying out the retrieval of information or investigation in microblogs, are particularly concerned by this subject. In this paper we present a state of the art on the identification of uncertainty in microblogs with the aim of identifying this issue and describing the current knowledge through the study of similar or related work. We mainly constated that, to adapt to the characteristics of social media, it is necessary to identify the uncertainty based on the contextual uncertain semantics rather than the traditional cue-phrases, and considering multiple sub-classes could provide more information for research on handing uncertainty in social media texts.