Conflict Analysis for Turkish Debates Using Text Mining and Text Segmentation Techniques
In Today’s World, we have so many discussions and debates that seem as problems. However, when we examine them technically, it is easy to understand that they are actually not problems but there are lack of communication and misunderstandings between people. At this point, it is crucial to explain the aim of this work. The main purpose is to show that languages can be analysed technically, and meanings of words and sentences can be understood through sentiment points. These points can be accepted as almost same for every language so that this type of work can be adapted to any of them. In this work, Turkish language is selected for examination purpose because there is not much work related with this language. Moreover, this work should be counted as experimental because the database that we are using is from another language that is English. That is translated to Turkish for the sake of our work. It is important to know that these results should be increased by other works and experiments so that more accurate outputs will occur.
Conflict Analysis is one of the most challenging issues in the world that many organizations and governments try to carry out perfectly. It is crucial to have a correct analysis to prepare a resolution for a problem. Thus, this thesis paper focuses on the ways that a software program can detect the reasons of arguments in a debate. The examples of debate dialogs are chosen from Turkish language because there is not much research in this area with this language. Moreover, the techniques which are applied in this work can also be applied to other languages, because a sentiment word dictionary is used, and sentiments are almost the same in every language. This is a prepared dictionary from SentiWordNet with all the sentiment points for English words. It is translated and extended for the Turkish language. Furthermore, both machine learning and lexicon-based approaches are implemented in order to increase the diversity of results. This paper aims to show that languages can be processed in a technical manner and meanings can be extracted from sentences to understand the reasons of arguments. Likewise, the main contribution of this thesis is that conflict analysis for Turkish debates can be applied with the techniques which are examined here, and they are also suitable for other languages.
Above paragraphs are taken from my master thesis and I would like to share it here, so that new researches can be done on top of that. I hope that my research can help to those who wants to study in these topics. You can find my complete thesis paper from the link below.
— — — — — — — —— —→ [PDF Link] ← — — — — — — — — — —
Note: You can also check other articles related to Computer Science and Engineering on my blog.
