臺灣博碩士論文加值系統

近十年來，社群網路在網際網路中表現活躍。使用者可能隨時隨地發佈訊息於社群網路，因此社群網路資料得以顯示社群網路使用者的地理位置。而顯示使用者地理位置將有助於近程資訊應用如：緊急救援、協尋失蹤人口得以實行；遠程如揭示區域以助於文化差異情感分析。本篇論文提出了分析twitter語料的語意以即時判斷使用者地理位置的方法。實驗由Amazon Mechanical Turk上的93位網路使用者判定結果的正確性。判定的資料為遍佈於全球17個國家的654位twitter使用者所發佈的2165則twitter。實驗結果顯示，本文的研究方法得以適用推論判斷使用者的所在國家，正確率為79%；推論判斷使用者目前所在地理位置正確率為66%。此結果顯示本論文所提出的方法可行性以及便利性。

In the last decade, the Internet has seen the rise of social networking as the number one online activity worldwide. To estimate the geographical location of users of social networks at a particular moment, we propose an approach to geo-tag Twitter users based only on their content of their posts. These data can later be used for local sentimental analysis, emergency detection, nding a missing person, and other novel location-based purposes. Our approach carried out a semantic analysis of tweets content to infer where in the globe a particular user is located at a given time. Based on our experimental results conducted through Amazon Mechanical Turk, the proposed framework was evaluated by 93 evaluators who assessed 654 twitter user proles and 2,165 tweets from 17 countries. Our system could infer some geographical information for 81% of evaluated proles. Results show 79% accuracy in identifying the user's country and 66% accuracy in identifying the users current location. This high accuracy shows our proposed methods are feasible and convincing.

Summary 1
Acknowledgments 2
List of Tables 5
List of Figures 6
1 Introduction 7
2 Related Work 10
3 Data Sources 12
4 Framework 14
4.1 Baseline Classication . . . . . . . . . . . . 16
4.2 Rule Generation . . . . . . . . . . . . . . . 17
4.3 Location Discovery . . . . . . . . . . . . . 18
4.4 Toponyms Removal . . . . . . . . . . . . . . 19
4.4.1 Country Discovery . . . . . . . . . . . . . 20
4.4.2 Inner Region Discovery . . . . . . . . . . 20
4.4.3 Web Search . . . . . . . . . . . . . . . . 21
4.5 Timeline Sorting . . . . . . . . . . . . . . 21
4.6 Location Inferred . . . . . . . . . . . . . 24
5 Experiments 25
5.1 Experimental Setup . . . . . . . . . . . . . 25
5.2 Experimental Results. . . . . . . . . . . . . 26
6 Conclusions and Future Work 29
Bibliography 31

[1] E. Amitay, N. Har'El, R. Sivan, and A. Soer. Web-a-where: geotagging web content.
SIGIR '04 Proceedings of the 27th annual international ACM SIGIR conference on
Research and development in information retrieval, pages 273{280, 2004.
[2] M. Ankerst, M. M. Breunig, H.-P. Kriege, and J. Sanderl. Optics: ordering points
to identify the clustering structure. SIGMOD '99 Proceedings of the 1999 ACM
SIGMOD international conference on Management of data, (6), 1999.
[3] A. E. Cano, A. Varga, and F. Ciravegna. Volatile classication of point of interests
based on social activity streams. In Proceedings of the 10th International Semantic
Web Conference, 2011.
[4] Z. Cheng, J. Caverlee, and K. Lee. You are where you tweet: A content-based
approach to geo-locating twitter users. CIKM '10 Proceedings of the 19th ACM
international conference on Information and knowledge management, pages 759{768,
2010.
[5] A. Doan. Analyzing and integrating social media. In NSF, editor, NSF Workshop on
Social Networks and Mobility in the Cloud, Arlignton, United States, Feb. 2012.
[6] Geonames Team. Geonames Geographical Database. http://www.geonames.org.
[Online; accessed April-2012].
[7] K. Lee, J. Caverlee, and S. Webb. Uncovering social spammers: Social honeypots
+ machine learning. SIGIR '10 Proceedings of the 33rd international ACM SIGIR
conference on Research and development in information retrieval, pages 435{442,
2010.
[8] Princeton University. Wordnet: A lexical database for English. http://wordnet.
princeton.edu/. [Online; accessed April-2012].
[9] T. Sakaki, M. Okazaki, and Y. Matsuo. Earthquake shakes twitter users: real-time
event detection by social sensors. WWW '10 Proceedings of the 19th international
conference on World wide web, pages 851-860, 2010.
[10] A. Santos, N. McGuckin, H. Y. Nakamoto, D. Gray, and S. Liss. Summary of travel
trends : 2009 national household travel survey. Technical Report FHWA-PL-ll-022,
U.S Department of Transportation ,Federal Highway Administration, June 2011.
[11] A. Scharl. Towards the geospatial web: Media platforms for managing geotagged
knowledge repositories. In A. Scharl and K. Tochtermann, editors, The Geospatial
Web, Advanced Information and Knowledge Processing, pages 3{14. Springer London.
[12] Stefan Kuhn and Kolossos. WikiProjekt Georeferenzierung. http://de.wikipedia.
org/wiki/Wikipedia:WikiProjekt_Georeferenzierung/Wikipedia-World/en.
[Online; accessed April-2012].
[13] A. Stefanidis, A. Crooks, and J. Radzikowski. Harvesting ambient geospatial information
from social media feeds. GeoJournal, pages 1{20, 2011.
[14] TheGeekCity.com. How fast are the airplanes? http://www.thegeekcity.com/how_
fast_are_the_airplanes/. [Online; accessed April-2012].
[15] Twitter. Twitter turns six. http://blog.twitter.com/2012/03/
twitter-turns-six.html, March 2012. [Online; accessed April-2012].
[16] S. Vieweg, A. L. Hughes, K. Starbird, and L. Palen. Microblogging during two
natural hazards events: What twitter may contribute to situational awareness. CHI
'10 Proceedings of the 28th international conference on Human factors in computing
systems, pages 1079{1088, 2010.