Product Attribute Extraction Based Real-Time C2C Matching of Microblogging Messages

Mohamed Rilf, Dilum Bandara1, Surangika Ranathunga2

  • 1University of Moratuwa
  • 2University of Moratuwa, Sri Lanka

Details

Category

Poster Sessions

Sessions

10:00 - 10:30 | Wed 30 May | 1st Floor Lobby | ERU

ERU Symposium Poster Session 1

15:15 - 15:45 | Wed 30 May | 1st Floor Lobby | ERU

ERU Symposium Poster Session 2

10:00 - 10:30 | Thu 31 May | 1st Floor Lobby | ERU

ERU Symposium Poster Session 3

15:15 - 15:45 | Thu 31 May | 1st Floor Lobby | ERU

ERU Symposium Poster Session 4

Full Text

Abstract

We describe a solution for real-time matching of microblogging messages related to product selling or buying. C2C buy/sell interest matching in real time is nontrivial due to the complexities of interpreting social media messages, number of messages, and diversity of products/services. Therefore, we adopt a combination of techniques from natural language processing, complex event processing, and distributed systems. First, we convert the message into semantics using named-entity recognition with CRF and Logistic Regression. Then the extracted data are matched using a complex event processor. Moreover, NoSQL and inmemory computing are used to enhance the scalability and performance. The proposed solution shows a high accuracy where classification and CRF models recorded an accuracy of 98.5% and 82.07% when applied to a real-world dataset. Low latency was observed for information extraction, in-memory data manipulation, and complex event processing were latencies were 0.5 ms, 5 ms, and 3.6 ms, respectively.

Additional Information

No information added

Video

No videos found