While the task of manually extracting arguments from large collections of opinionated text is an intractable one, a tool for computerassisted extraction can (i) select a subset of the text collection that contains re-occurring arguments to minimise the amount of text that the human coder has to read, and (ii) present the selected texts in a way that facilitates manual coding of arguments. We propose a tool called Topics2Themes that uses topic modelling to extract important topics, as well as the terms and texts most closely associated with each topic. We also provide a graphical user interface for manual argument coding, in which the user can search for arguments in the texts selected, create a theme for each type of argument detected and connect it to the texts in which it is found. Topics, terms, texts and themes are displayed as elements in four separate lists, and associations between the elements are visualised through connecting links. It is also possible to focus on one particular element through the sorting functionality provided, which can be used to facilitate the argument coding and gain an overview and understanding of the arguments found in the texts.
@InProceedings{SKEPPSTEDT18.2, author = {Maria Skeppstedt and Kostiantyn Kucher and Manfred Stede and Andreas Kerren}, title = {Topics2Themes: Computer-Assisted Argument Extraction by Visual Analysis of Important Topics}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {may}, date = {7-12}, location = {Miyazaki, Japan}, editor = {Mennatallah El-Assady and Annette Hautli-Janisz and Verena Lyding}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-13-9}, language = {english} }
Summary of the paper