An Intelligent System for Predicting Location from Text Content on Social Media


DEMİRCİ M. S., Ozdemir S. O.

2017 International Conference on Computer Science and Engineering (UBMK), Antalya, Türkiye, 5 - 08 Ekim 2017, ss.671-676 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/ubmk.2017.8093496
  • Basıldığı Şehir: Antalya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.671-676
  • Gazi Üniversitesi Adresli: Evet

Özet

In this study, we have presented an approach to show how location detection can be possible by using social media posts of Internet users. To this end, we have developed a software program to show that locations of Twitter users can be detected just by analyzing the contents of their tweets, even if they hide the location data coming from the background of the tweet. We have collected text-based data from Twitter which are posted by users in istanbul, Ankara, and izmir, the largest cities of Turkey according to population. After presenting the preprocessed data in vector space model, we have trained our system using the data by means of Naive Bayes Classifier. After the testing process, experimental results have shown that locations of Twitter users can be detected just by analyzing the contents of their publicly available tweets in the absence of location data with 54.57% accuracy rate for the mentioned three cities of Turkey.