Discourse relations in rationale‐containing text‐segments

Abstract

Offering one's perspective and justifying it has become a common practice in online text-based communications, just as it is in typical, face-to-face communication.Compared to the face-to-face communications, it can be particularly more challenging for users to understand and evaluate another's perspective in online communications. On the other hand, the availability of the communication record in online communications offers a potential to leverage computational techniques to automatically detect user opinions and rationales. One promising approach to automatically detect the rationales is to detect the common discourse relations in rationale texts. However, no empirical work has been done with regard to which discourse relations are commonly present in the users' rationales in online communications. To fill this gap, we annotated the discourse relations in the text segments that contain the rationales (N 5 527 text segments). These text segments are obtained from five datasets that consist of five online posts and the first 100 comments. We identified 10 discourse relations that are commonly present in this sample. Our finding marks an important contribution to this rationale detection approach. We encourage more empirical work, preferably with a larger sample, to examine the generalizability of our findings.

An ensemble clustering approach for topic discovery using implicit text segmentation

“…topics) in the document summarization, wherein each topic contains a final summary to ensure that it provides all the unique topics in the text document. However, a document is segmented through the regions of words which is considered as weakest approach as suggested by the previous work [4]. In addition, segments are retrieved using lexical relationship among words, and hence, such segments do not possess enough cohesiveness.…”