Determining comments worthy to read.

Status


Finished master thesis

Student


  • Seyedeh Ziyaei

Formalia


Targeted audience
  • AI Master
Preconditions
  • Ability to read and understand papers written in English.
  • Ability to perform academic writing.
  • Strong programming skills (e.g.Java, App programming essential)
  • Lectures Information Retrieval oder Information Mining, Deep Learning (essential)

Task description


A majority of online news articles attract user comments, however, not all of them carry relevant information for journalists and editors. News reporters can use comments to understand readers' needs and opinions, track new emerging topics or organize the news reporting to increase engagement from the readers. Other uses of comments could also emerge if a technology existed that could identify comments worthy engaging with and discard the worthless commentary.

This Master Thesis project will investigate how to determine worthy comments. One sort of comments that are worth reading and engaging with are those that carry arguments, i.e. claims that are supported or refuted by evidence. Therefore, this project will investigate argumentation mining as the key innovative technology behind comment worthiness scoring. First it will perform user studies proofing that news worhty comments are those that are argumentative. Optionally the candidate will also develop argument mining for conversations and apply to worthiness scoring of user generated comments.

Tasks:

  • Literature scan. This should be done before the actual project starts. Here the student will be given some initial papers. Based on these papers the student should collect more papers, perform a review of all the papers and prepare an oral presentation of 30 mins. providing an intro to the field. This should take 2-3 weeks. Actual work:
  • Preparing and condacting the user studies. Analysing the results.
  • Optionally developing a deep learning based argument mining system for news comments.