Uncertainty Identification in Microblogs

Microblogging, like Twitter, has grown in popularity as a medium for human expression, allowing users to quickly create content on breaking news, public events, or products. The vast volume of microblogging data is a valuable and timely source of public attitudes, views, and opinions on a variety of issues. Users express themselves freely with varied degrees of uncertainty, which makes using microblogs as a data source a tedious task that necessitates the consideration of this factor. We're talking about the uncertainty expressed in microblogs, not the one relative to the claimed information factuality. This aspect of microblogging that we are addressing has gotten little attention, despite the fact that it is critical to understand the degree of ambiguity with which users plan to share information. This topic is particularly relevant to research projects involving information retrieval or investigation in microblogs. 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 concluded 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.