Title :
Twitter Information Extraction for Smart City
Author :
Hanifah, Raidah ; Supangkat, Suhono Harso ; Purwarianti, Ayu
Author_Institution :
Sch. of Electr. & Inf. Eng., Bandung Inst. of Technol., Bandung, Indonesia
Abstract :
In Indonesia, Bandung is the second most active Twitter user, which means a lot of tweets have been shared among Bandung people on Twitter. Tweets can be used as a data source to explore information related to the city. One example is information related to traffic congestion, such as information of location, date, and time when the traffic congestion happened. In this study, we proposed a method to filter the tweets related to traffic congestion in Bandung and to extract the information of location, time, date and image (if any). SVM with several variations of the weighting and the selection of features is used for filtering process. The results showed that the greatest accuracy rate is 83% use Binary weighting method in top-2000 features. Meanwhile, information extraction process carried out by a rule-based approach, gave satisfactory results, around 98%-100% for the extraction of date, time and URL. However, the extraction of location information only gave accuracy of about 62%. It was caused by OOV (Out of Vocabulary) and OOR (Out of Rules).
Keywords :
feature selection; information filtering; knowledge based systems; public administration; smart cities; social networking (online); support vector machines; traffic engineering computing; Bandung traffic congestion; Indonesia; OOR; OOV; SVM; Twitter information extraction; binary weighting method; feature selection; filtering process; out of rules; out of vocabulary; rule-based approach; smart city; support vector machine; Accuracy; Cities and towns; Data mining; Feature extraction; Twitter; Uniform resource locators; Support Vector Machine (SVM); Twitter; information extraction; social sensor; traffic congestion;
Conference_Titel :
ICT For Smart Society (ICISS), 2014 International Conference on
Conference_Location :
Bandung
DOI :
10.1109/ICTSS.2014.7013190
