（2004）Mining Textual Contents of Financial Reports.pdfVIP

The International Journal of Digital Accounting Research 1 Vol. 4, N. 7, 2004, pp. 1-29 ISSN: 1577-8517 Mining Textual Contents of Financial Reports1 Antonina Kloptchenko. Åbo Akademi University, Turku, Finland. akloptch@abo.fi Camilla Magnusson. University of Helsinki, Helsinki, Finland. camilla.magnusson@helsinki.fi Barbro Back. Åbo Akademi University, Turku, Finland. barbro.back@abo.fi Ari Visa. Tampere University of Technology, Tampere, Finland. ari.visa@cs.tut.fi Hannu Vanharanta. Pori School of Technology and Economics, Pori, Finland. hannu.vanharanta@pori.tut.fi Abstract. The message, stylistic focus, language and readability of financial reports are good indicators of the perspectives and developments of any company. These indicators can guide companiesʼ decision makers to more efficient actions in the dynamic business environment. In this paper, we have studied the language and contents of quarterly financial reports using automated linguistic and text mining methods. We aim at comparing the results from linguistic analysis of quarterly reports by means of collocational networks and the results obtained from text mining analysis of quarterly report by means of the prototype matching. We perform the study on the quarterly reports from three leading companies in the telecommunications sector. Our results are somewhat controversial: some of the reports from the companies have as their closest matches the reports with similar collocational networks and some do not have. Key words: Text Mining, Annual Reports, Prototype Matching Method, Collocational Networks. 1 The research was presented at the XXVI Annual Congress of the European Accounting Association, 2-4 April, 2003, Seville, Spain. We gratefully acknowledge the financial support of TEKES (grant number 47 533). We are grat