Linking Social Media Posts to News with Siamese Transformers

01/10/2020
by   Jacob Danovitch, et al.
0

Many computational social science projects examine online discourse surrounding a specific trending topic. These works often involve the acquisition of large-scale corpora relevant to the event in question to analyze aspects of the response to the event. Keyword searches present a precision-recall trade-off and crowd-sourced annotations, while effective, are costly. This work aims to enable automatic and accurate ad-hoc retrieval of comments discussing a trending topic from a large corpus, using only a handful of seed news articles.

READ FULL TEXT

page 4

page 7

research
05/16/2020

Measuring and Characterizing Hate Speech on News Websites

The Web has become the main source for news acquisition. At the same tim...
research
04/07/2018

Quootstrap: Scalable Unsupervised Extraction of Quotation-Speaker Pairs from Large News Corpora via Bootstrapping

We propose Quootstrap, a method for extracting quotations, as well as th...
research
09/24/2020

Understanding the Use of Fauxtography on Social Media

Despite the influence that image-based communication has on online disco...
research
04/04/2019

MMED: A Multi-domain and Multi-modality Event Dataset

In this work, we construct and release a multi-domain and multi-modality...
research
06/24/2020

XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference

Automatic identification of mentioned entities in social media posts fac...
research
01/12/2017

Single-Pass, Adaptive Natural Language Filtering: Measuring Value in User Generated Comments on Large-Scale, Social Media News Forums

There are large amounts of insight and social discovery potential in min...
research
10/31/2019

Which Factors Impact Engagement on News Articles on Facebook?

Social media is increasingly being used as a news-platform. To reach the...

Please sign up or login with your details

Forgot password? Click here to reset