Research Seminar by Joonsuk Park | Evaluative Argument Mining and Its Applications

Evaluative Argument Mining and Its Applications
 

The ease of internet access has significantly increased the number of user comments authored by inexperienced writers. Despite the potential usefulness of such comments, readers face the daunting task of sifting through copious amounts of uninformative content to extract relevant information. One popular approach to deal with this problem is to build systems that can help readers by recommending helpful comments or summarizing available information. We, however, consider the problem from the perspective of commenters: Can we build a system that can guide commenters to write “better” comments? Such an approach would enhance the overall quality of textual content available online and complement existing solutions for reader assistance.

In this talk, I will present the core components of an automated system to assist commenters in constructing better-structured arguments in their comments. These include: (1) A theoretical  argumentation model to capture the evaluability of arguments in the online setting, (2) A classifier for determining an appropriate type of support---reason or evidence---for propositions comprising user comments, (3) A classifier for identifying support relations present in user comments. I will also discuss how this system can be applied to practical applications such as assistive commenting interfaces and recommendation systems.