Event detection on social media using transaction based stream processing engine

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Fen Bilimleri Enstitüsü, Türkiye

Tezin Onay Tarihi: 2019

Tezin Dili: İngilizce

Öğrenci: HÜSEYİN ALPER ÇINAR

Danışman: Pınar Karagöz

Özet:

The aim of this study is detecting events on social media by improving current solutions in terms of accuracy and time performance. An event is something that occurs in a short duration of time in a certain place. In this thesis, the problem is modelled as a streaming transaction process. Three different event detection method is adapted to our solution. First one is the keyword-based event detection method that looks for bursty keywords in a period. The second one is the clustering-based event detection method which is a version of the hierarchical clustering algorithm. And the last one is the hybrid event detection method of keyword-based and clustering-based algorithms. To specify the problem as streaming transaction process, all algorithms are implemented on top of S-Store. S-Store is a streaming OLTP engine having distributed, scalable and guaranteed ordered delivery features. All of the event detection methods are run and evaluated their performance with a real data set obtained from Twitter.