Description
One way to explore a city is to know what people do on their leisure. Looking for local events and promotions is a common need for most people during travel or moving to a new city. However, delivering such messages to the right people is still a challenge for small businesses that do not sell tickets on high-end websites. Instead, most events are usually distributed by posting on social networking sites like Facebook. To fulfill such information need, we consider information technologies to extract events from 230K Facebook fan pages to build an event database and provide a social event search service. The technologies includes web scraping and web data extraction as well as natural language processing techniques for event names and venues recognition. We show how to speed up training data preparation through locality sensitive hashing (LSH) on seed lists based on distant supervision as well as how to improve the training data quality via double-tier automatic labeling. In addition to the demonstration of event search service provided by EventGo, we also disclose statistics in the events extracted from Facebook Fan Pages and Facebook events, showing the change in the ad market.| Period | 23 Sep 2020 → 26 Sep 2020 |
|---|---|
| Held at | Tokyo Metropolitan University, Japan |
Keywords
- Social networking (online)
- Data mining
- Urban areas
- Training data
- Fans
- System integration