Neural language representations predict outcomes of scientific research

• DOI: 10.48550/arxiv.1805.06879
• Publication Date: 2018-01-01
• Authors: James P. Bagrow; Daniel Berenberg; Joshua Bongard
• Keywords: 0301 basic medicine; FOS: Computer and information sciences; Computer Science - Machine Learning; 0303 health sciences; Computer Science - Computation and Language; Computer Science - Artificial Intelligence; Machine Learning (stat.ML); Machine Learning (cs.LG); Computer Science - Computers and Society; 03 medical and health sciences; Artificial Intelligence (cs.AI); Statistics - Machine Learning; Computers and Society (cs.CY); Computation and Language (cs.CL)

Many research fields codify their findings in standard formats, often by reporting correlations between quantities of interest. But the space all testable correlates is far larger than scientific resources can currently address, so ability to accurately predict would be useful plan and allocate resources. Using a dataset approximately 170,000 correlational extracted from leading social science journals, we show that trained neural network reported using only text descriptions correlates. Accurate predictive models such as these guide scientists towards promising untested correlates, better quantify information gained new findings, has implications for moving artificial intelligence systems predicting structures relationships real world.