We critically assess mainstream accounting and finance research applying methods from computational linguistics (CL) to study financial discourse. We also review common themes and innovations in the literature and assess the incremental contributions of studies applying CL methods over manual content analysis. Key conclusions emerging from our analysis are: (a) accounting and finance research is behind the curve in terms of CL methods generally and word sense disambiguation in particular; (b) implementation issues mean the proposed benefits of CL are often less pronounced than proponents suggest; (c) structural issues limit practical relevance; and (d) CL methods and high quality manual analysis represent complementary approaches to analyzing financial discourse. We describe four CL tools that have yet to gain traction in mainstream AF research but which we believe offer promising ways to enhance the study of meaning in financial discourse. The four tools are named entity recognition (NER), summarization, semantics and corpus linguistics.
We provide a methodological contribution by developing, describing and evaluating a method for automatically retrieving and analysing text from digital PDF annual report files published by firms listed on the London Stock Exchange (LSE). The retrieval method retains information on document structure, enabling clear delineation between narrative and financial statement components of reports, and between individual sections within the narratives component. Retrieval accuracy exceeds 95% for manual validations using a random sample of 586 reports. Large-sample statistical validations using a comprehensive sample of reports published by non-financial LSE firms confirm that report length, narrative tone and (to a lesser degree) readability vary predictably with economic and regulatory factors. We demonstrate how the method is adaptable to non-English language documents and different regulatory regimes using a case study of Portuguese reports. We use the procedure to construct new research resources including corpora for commonly occurring annual report sections and a dataset of text properties for over 26,000 U.K. annual reports.
9 August 2014 in Language Resources and Evaluation
The semantically complicated Arabic natural vocabulary, and the shortage of available techniques and skills to capture Arabic emotions from text hinder Arabic sentiment analysis (ASA). Evaluating Arabic idioms that do not follow a conventional linguistic framework, such as contemporary standard Arabic (MSA), complicates an incredibly difficult procedure. Here, we define a novel lexical sentiment analysis approach for studying Arabic language tweets (TTs) from specialized digital media platforms. Many elements comprising emoji, intensifiers, negations, and other nonstandard expressions such as supplications, proverbs, and interjections are incorporated into the MULDASA algorithm to enhance the precision of opinion classifications. Root words in multidialectal sentiment LX are associated with emotions found in the content under study via a simple stemming procedure. Furthermore, a feature–sentiment correlation procedure is incorporated into the proposed technique to exclude viewpoints expressed that seem to be irrelevant to the area of concern. As part of our research into Saudi Arabian employability, we compiled a large sample of TTs in 6 different Arabic dialects. This research shows that this sentiment categorization method is useful, and that using all of the characteristics listed earlier improves the ability to accurately classify people’s feelings. The classification accuracy of the proposed algorithm improved from 83.84% to 89.80%. Our approach also outperformed two existing research projects that employed a lexical approach for the sentiment analysis of Saudi dialects.
In this paper we present our generic extractive Arabic and English multi-document summarisers. We also describe the use of machine translation for evaluating the generated Arabic multi-document summaries using English extractive gold standards. In this work we first address the lack of Arabic multi-document corpora for summarisation and the absence of automatic and manual Arabic gold-standard summaries. These are required to evaluate any automatic Arabic summarisers. Second, we demonstrate the use of Google Translate in creating an Arabic version of the DUC-2002 dataset. The parallel Arabic/English dataset is summarised using the Arabic and English summarisation systems. The automatically generated summaries are evaluated using the ROUGE metric, as well as precision and recall. The results we achieve are compared with the top five systems in the DUC-2002 multi-document summarisation task.