Learning Tone and Attribution for Financial Text Mining

Learning Tone and Attribution for Financial Text Mining Mahmoud El-Haj1 , Paul Rayson1 , Steven Young1, Andrew Moore1, Martin Walker2, Thomas Schleicher2, Vasiliki Athanasakou3 1Lancaster University, UK 2University of Manchester, UK 3London School of Economics, UK Abstract Attribution bias refers to the tendency of people to attribute successes to their own abilities but failures to external factors. In a business context an internal factor might be the restructuring of the firm and an external factor might be an unfavourable change in exchange or interest rates. In accounting research, the presence of an attribution bias has been demonstrated for the narrative sections of the annual financial reports. Previous studies have applied manual content analysis to this problem but in this paper we present novel work to automate the analysis of attribution bias through using machine learning algorithms. Previous studies have only applied manual content analysis on a small scale to reveal such a bias in the narrative section of annual financial reports. In our work a group of experts in accounting and finance labelled and annotated a list of 32,449 sentences from a random sample of UK Preliminary Earning Announcements (PEAs) to allow us to examine whether sentences in PEAs contain internal or external attribution and which kinds of attributions are linked to positive or negative performance. We wished to examine whether human annotators could agree on coding this difficult task and whether Machine Learning (ML) could be applied reliably to replicate the coding process on a much larger scale. Our best machine learning algorithm correctly classified performance sentences with 70% accuracy and detected tone and attribution in financial PEAs with accuracy of 79%. Keywords: PEA, financial, narratives, machine learning, string vectors, NLP, semantic, part of speech, tagger 1. Introduction In social science, attribution bias refers to human beings’ tendency to attribute successes to their own abilities but failures to external factors. In the financial domain, inter- nal factors for an organisation could include cost reduction programmes and employee training, while external factors include movements in exchange or interest rates. In ac- counting research, the presence of an attribution bias has been demonstrated for the narrative sections of annual fi- nancial reports (AFRs). For instance, Clatworthy and Jones (Clatworthy and Jones, 2003) confirm the existence of an attribution bias in the UK Chairman’s Statement sections of AFRs when they find that statements about last year’s pos- itive financial performance are typically explained through superior management skills whereas statements about neg- ative financial performance are typically attributed to un- favourable factors outside the firm’s control. Similar find- ings are reported in Aerts (Aerts, 1994), Aerts (Aerts, 2005) and Hooghiemstra (Hooghiemstra, 2000). All previous studies have applied manual content analysis to the exami- nation of attribution bias in narratives. The experiment pre- sented here breaks new ground by quantifying the difficulty of the manual annotation task in a new type of financial nar- rative and by attempting to automate the analysis of attribu- tion bias in order to scale up the analysis for …

Content truncated to 500 words