Causal Knowledge Extraction from Scholarly Papers in Social Sciences

TL;DR

This paper presents NLP models that automatically identify hypotheses, causal relationships, and cause-effect entities in social science scholarly papers to facilitate knowledge extraction and synthesis.

Contribution

The paper introduces a set of NLP models for classifying hypotheses, detecting causality, and extracting cause-effect entities from social science texts, demonstrating high performance.

Findings

High accuracy in hypothesis classification

Effective causality detection in hypotheses

Successful extraction of cause and effect entities

Abstract

The scale and scope of scholarly articles today are overwhelming human researchers who seek to timely digest and synthesize knowledge. In this paper, we seek to develop natural language processing (NLP) models to accelerate the speed of extraction of relationships from scholarly papers in social sciences, identify hypotheses from these papers, and extract the cause-and-effect entities. Specifically, we develop models to 1) classify sentences in scholarly documents in business and management as hypotheses (hypothesis classification), 2) classify these hypotheses as causal relationships or not (causality classification), and, if they are causal, 3) extract the cause and effect entities from these hypotheses (entity extraction). We have achieved high performance for all the three tasks using different modeling techniques. Our approach may be generalizable to scholarly documents in a wide range of social sciences, as well as other types of textual materials.