An Empirical Study on Uncertainty Identification in Social Media Context

Abstract

Uncertainty text detection is important to many social-media-based applications since more and more users utilize social media platforms (e.g., Twitter, Facebook, etc.) as information source to produce or derive interpretations based on them. However, existing uncertainty cues are ineffective in social media context because of its specific characteristics. In this paper, we propose a variant of annotation scheme for uncertainty identification and construct the first uncertainty corpus based on tweets. We then conduct experiments on the generated tweets corpus to study the effectiveness of different types of features for uncertainty text identification.

Annotating omission in statement pairs

“…Further work includes analyzing whether the changes in the omission examples contain also changes of uncertainty class (Szarvas et al, 2012) or bias type (Recasens et al, 2013), as well as expanding the notion of omission to the detection of the loss of detail in paraphrases. Moreover, we want to explore how to identify the most omissionprone news types, in a style similar to the characterization of unreliable users in Wei et al (2013).…”

A Unified Framework to Identify and Extract Uncertainty Cues, Holders, and Scopes in One Fell-Swoop

“…As I mentioned earlier in Chapter 1, there is a plethora of work on uncertainty annotation for English (Rubin, 2007;Szarvas et al, 2008;Saurí and Pustejovsky, 2009;Matsuyoshi et al, 2010;Farkas et al, 2010;Rubinstein et al, 2013;Wei et al, 2013), Japanese (Hendrickx et al, 2012), Chinese (Cui and Chi, 2013), Portuguese (Hendrickx et al, 2012;Avila and Mello, 2013), and Hungarian (Vincze, 2014). However, prior to my own preliminary work (Al-Sabbagh et al, 2014a) and the work I presented in this chapter, there are no Arabic uncertainty-annotated corpora, to the best of my knowledge.…”

“…• the annotated languages, genres, and domains: most corpora are for the English language (Rubin, 2007;Szarvas et al, 2008;Saurí and Pustejovsky, 2009;Farkas et al, 2010;Rubinstein et al, 2013;Wei et al, 2013), except for a few annotation projects for Portuguese (Hendrickx et al, 2012;Avila and Mello, 2013), Chinese (Wei et al, 2013), and Hungarian (Vincze, 2014). e most widely covered domains and genres for uncertainty annotation are Wikipedia (Farkas et al, 2010;Vincze, 2014), biomedical texts (Szarvas et al, 2008;Vincze, 2014), and newswire texts (Rubin, 2007;Szarvas et al, 2008;Vincze, 2014).…”

“…As a result, no much a ention has been given to uncertainty a ribution. Besides, some researchers have just decided to dedicate more time and e ort to uncertainty detection and scope extraction for no clear reasons (Baker et al, 2012;Wei et al, 2013). With a highly interactive linguistic genre such as tweets, default and prototypical holders are unlikely to work:…”

“…ere is a plethora of work on English (Matsuyoshi et al, 2010;Prabhakaran, 2010;Rubin, 2007;Rubinstein et al, 2013;Ruppenhofer and Rehbein, 2012;Saurí and Pustejovsky, 2009;Szarvas et al, 2008;Tang et al, 2010;Vincze et al, 2011;Wei et al, 2013), French (Goujon, 2009), Portuguese (Hendrickx et al, 2012;Avila and Mello, 2013), and Swedish (Mowery et al, 2012), yet nothing for agglutinative morphologically-rich languages except for Hungarian (Vincze, 2014). One reason for the li le research on agglutinative morphologically-rich languages with a exible word order is the lack of uncertainty-annotated corpora for such languages.…”