Tracking human mobility using Twitter through natural language processing techniques
Date of Publication
Master of Science in Computer Science
College of Computer Studies
Charibeth K. Cheng
Defense Panel Chair
Ethel C. Ong
Defense Panel Member
Charibeth K. Cheng
Courtney Anne M. Ngo
Rafael A. Cabredo
Social media has been proven to be a reliable source of user-generated data that can be used to extract important information regarding different topics, one of which is tracking human mobility. Information on human mobility, which pertains to human travel patterns, can be retrieved from social media, since people of all ages post all sorts of updates on various social media sites, including updates on the places they visit all throughout the day. This research built a system that extracts location, activity and time information from tweets using natural language processing techniques in order to present and visualize human mobility patterns on a layered map. It was discovered that people who post in Manila seldom use the GPS on their phones, so there is a need to extract the information from the tweet content itself. Based on the results, it is possible to extract location and activity information using POS tags. It was also observed in this study that the activity done by the user is usually related to the location. However, it was also revealed that activities are usually not explicitly stated in the text. With that being said, the time information must not be dependent on the presence or the tense of the verb in the tweet. Lastly, it was discovered that tweets are not sufficient and cannot be the sole source of data for human mobility. It also lacks information for urban planning, but the information retrieved and the patterns observed from the visualization reveal that these information may be useful for other fields such as advertising and marketing.
Archives, The Learning Commons, 12F Henry Sy Sr. Hall
1 computer disc ; 4 3/4 in.
Natural language processing (Computer science); Social networks
Ver, A. O. (2018). Tracking human mobility using Twitter through natural language processing techniques. Retrieved from https://animorepository.dlsu.edu.ph/etd_masteral/5584