Early Discovery of Emerging Entities in Microblogs
This addresses the need for timely social-trend analysis and marketing research by enabling early detection of emerging entities, though it is incremental relative to prior unseen entity recognition methods.
The paper tackles the problem of distinguishing truly emerging entities from non-emerging ones in microblogs, proposing a method that achieves 83.2% precision for top discoveries and detects 80.4% of Wikipedia-registered entities with an average lead-time of 571 days.
Keeping up to date on emerging entities that appear every day is indispensable for various applications, such as social-trend analysis and marketing research. Previous studies have attempted to detect unseen entities that are not registered in a particular knowledge base as emerging entities and consequently find non-emerging entities since the absence of entities in knowledge bases does not guarantee their emergence. We therefore introduce a novel task of discovering truly emerging entities when they have just been introduced to the public through microblogs and propose an effective method based on time-sensitive distant supervision, which exploits distinctive early-stage contexts of emerging entities. Experimental results with a large-scale Twitter archive show that the proposed method achieves 83.2% precision of the top 500 discovered emerging entities, which outperforms baselines based on unseen entity recognition with burst detection. Besides notable emerging entities, our method can discover massive long-tail and homographic emerging entities. An evaluation of relative recall shows that the method detects 80.4% emerging entities newly registered in Wikipedia; 92.4% of them are discovered earlier than their registration in Wikipedia, and the average lead-time is more than one year (571 days).