Raimond: Quantitative Data Extraction from Twitter to Describe Events

Abstract

Abstract. Social media play a decisive role in communicating and spreading information during global events. In particular, real-time microblogging platforms such as Twitter have become prevalent. Researchers have used microblogging for a number of tasks, including past events analysis, predictions, and information retrieval. Nevertheless, little attention has been given to quantitative data extraction. In this paper, we address two questions: can we develop a mechanism to extract quantitative data from a collection of tweets, and can we use the salient findings to describe an event? To answer the first question, we introduce Raimond, a virtual text curator, specialized in quantitative data extraction from Twitter. To address the second question, we use our system on three events and evaluate its output using a crowdsourcing strategy. We demonstrate the effectiveness of our approach with a number of real world examples.

Unsupervised Numerical Information Extraction via Exploiting Syntactic Structures

“…For example, it can be difficult to summarize a dependency pattern between "plants" and "four" from the sentence "These plants originated from the Amazon jungle and can grow up to four feet high". Wang et al [23], Alonso and Sellam [24], Ravichander et al [25], Sellam and Alonso [26] extract small pieces of text which contain quantities from a CP tree. We argue that small pieces of text are not sufficient to fully understand the quantities; more details like the unit, quantity value, date, and some context are needed.…”