트위터를 이용한 실시간 이벤트 지역 탐지 시스템 = Twitter Based Realtime Event-Location Detector

다국어 초록 (Multilingual Abstract)

SNS is a web-based platform that helps to build or to keep relationships among people. SNS platforms in early stage including Friendster and MySpace were implemented for the desktop and laptop users. As more people access wireless internet using their mobile phones, SNS platforms can also have some important features such as "real-time access" and "location information". These two features make it possible to let people share their activities, interests, and observations in real-time at any places. Recently, most of SNS platforms including Twitter, Facebook, and Yelp use the location information of users. Therefore, if we consider a SNS user as a sensor that reports its observations at a specific location, it would be possible to detect events by analyzing their social contents. There have been already numbers of research on this topic have been published or still ongoing. Twitter has been widely used for conducting the research because it has important three features which are required to detect an event: time, location, and content. However, the most approaches struggle with detecting the location which is related to an event correctly. In this paper, we introduce a system that detects an event with its location in real-time based on increment of tweets that mention a specific location frequently. The result of performance evaluation shows that the proposed system detects an event in real-time. We also improved the system performance by reducing some noises from our system.

국문 초록 (Abstract)

SNS는 사용자들의 관계형성을 도와주는 웹 기반의 온라인 플랫폼 서비스이다. 기존 SNS 사용자들은 이를 이용하기 위해 주로 데스크톱이나 노트북을 이용하였다. 그러나 최근 스마트폰의 보급으로 인해 웹 접근성이 확대되면서 SNS 사용자가 크게 증가하였다. SNS를 이용하는 사용자들은 주로 자신의 일상이나 경험한 일들을 다른 사용자들과 공유한다. 이때 사용자 개인을 하나의 센서로 가정하고 그들이 남긴 콘텐츠를 분석할 수 있다면, 이를 이용해 현실에서 발생한 이벤트를 탐지할 수 있다. 이러한 시도는 이미 많은 연구에서 진행되고 있다. 특히 트위터의 경우 이벤트 탐지에 적합한 구조적 특징들로 인해 관련 분야에서 다양하게 활용되고 있다. 그러나 대부분의 선행 이벤트 탐지 연구들은 키워드에 의존하며 이벤트가 발생한 지역을 탐지하는 것에 있어 명확한 한계점을 지니고 있다. 이에 본 논문에서는 트위터에서 언급된 빈도가 급증한 지역들을 기반으로 이벤트가 발생한 지역을 실시간으로 탐지하는 TRED(Twitter based Realtime Event-location Detector) 시스템을 제안하였다. 이후 성능평가를 통해 제안하는 시스템이 실시간으로 동작할 수 있는지를 확인하였고, 실제 발생한 이벤트를 탐지함으로서 효율성을 입증하였다. 또한 노이즈 제거를 통한 탐지율 향상을 언급하였으며 향후 보다 높은 성능의 시스템에 대한 가능성을 보였다.

목차 (Table of Contents)

• 목 차
• 감사의 글 ···························································· iv
• 그림 목차 ···························································· vii
• 표 목차 ····························································· viii
• 초록 ··································································· ix
• 1. 서론 ································································· 1
• 2. 관련연구 ··························································· 4
• 3. 실시간 이벤트 지역 탐지 시스템 ······························· 6
• 3.1 트윗 데이터 수집 ·············································· 7
• 3.2 트윗 정제 ······················································ 8
• 3.3 트윗 분석 ······················································ 10
• 4. 실험 및 결과 ····················································· 13
• 4.1 성능 평가 ····················································· 13
• 4.2 이벤트 분석 ·················································· 15
• 5. 결론 ······························································· 20
• 참고문헌 ····························································· 21
• 영문논문제출서 ····················································· 23
• 영문인준서 ··························································· 24
• ABSTRACT ························································ 25