Abstract
We propose a novel and objective statistical method known as latent semantic analysis (LSA), used in search engine procedures and information retrieval applications, as a methodological alternative for textual analysis in corporate social responsibility (CSR) research. LSA is a language processing technique that allows recognition of textual associative patterns and permits statistical extraction of common textual themes that characterize an entire set of documents, as well as tracking the relative prevalence of each theme over time and across entities. LSA possesses all the advantages of quantitative textual analysis methods (reliability control and bias reduction), is automated (meaning it can process numerous documents in minutes, as opposed to the time and resources needed to perform subjective scoring of text passages) and can be combined in mixed-method research approaches. To demonstrate the method, our empirical application analyzes the CSR reports of Hellenic companies, and first testifies that eight (five) recurring and common textual themes can explain about 50% (40%) of the variation in their CSR reports. We further establish—via cross-sectional regression with selection—that the identified themes have a statistically significant effect on reporting firms’ return-on-assets (ROA), even after controlling for factors known to explain the cross-sectional variation in ROA and the self-selectivity of firms that engage in CSR practices.
Similar content being viewed by others
Notes
Riffe et al. (1998, p. 20) define quantitative content analysis as “the systematic and replicable examination of symbols of communication, which have been assigned numeric values according to valid measurement rules, and the analysis of relationships involving those values using statistical methods, in order to describe the communication, draw inferences about its meaning, or infer from the communication to its context, both of production and consumption”.
As in previous studies, we employ the terms ‘non-financial’ and ‘corporate social responsibility’ disclosure/reporting “synonymously, referring to accountability efforts linked to aspects of business activity that fall beyond the financial domain” (Evangelinos and Skouloudis 2014, p. 49).
Notable examples of country-specific quantitative content analysis studies on CSR reporting include Parsa and Kouhy (2008) for the United Kingdom; Ellerup Nielsen and Thomsen (2007) for Demark; Vuontisjärvi (2006) for Finland; Paul et al. (2006) for Mexico; Thompson and Zakaria (2004) for Malaysia, Frostenson et al. (2011) for Sweden; Mahadeo et al. (2011) for Mauritius; Zhao (2012) for China and Russia; Gao (2011) for China, Campopiano and De Massis (2014) and Satta et al. (2015) for Italy, Saeidi et al. (2015) for Iran, Higgins et al. (2015) for Australia and Alotaibi and Hussainey (2016) for Saudi Arabia.
We failed to locate any CSR report by Hellenic firms prior to 2001. Virtually all firms listed in the ASE that publish CSR reports do so in English, as more that 60% of the ASE’s capitalization is held by foreign (institutional) investors (as of May 2017; see the ASE monthly news releases).
CSR Hellas is a member of the European Business Network for Corporate Social Responsibility (CSR Europe), a platform for businesses looking to enhance sustainable growth and positively contribute to society, with over 10,000 companies as members.
See http://globalsustain.org for more information. The Global Reporting Initiative (GRI, https://www.globalreporting.org) is a leading organization in the sustainability field that promotes the use of sustainability reporting as a way for organizations to become more sustainable and contribute to sustainable development.
The two reports of Sample year 2001 that are not plotted in Fig. 3 for clarity purposes have 6148 and 6678 words/terms respectively. Note that in the remainder, the use of terms Hellenic or Greek sample firms are to be understood as including the sample MNCs that operate in Greece.
See Landauer, Foltz and Laham (1998) for an excellent review.
LSA might not require human-coding or pre-determined categories of interest, but also it does not preclude it, making the method appropriate for mixed (both human and software coding) approaches to quantitative content analysis (see Lock and Seele 2015).
See http://provalisresearch.com/ for details regarding the software; a recent paper by Satta et al. (2015) employs the same software in the context of voluntary corporate disclosure.
For interested readers, we make our complete, modified dictionary employed in this study available upon request.
The Porter (1980) stemming algorithm is inbuilt in WordStat®. More details regarding the algorithm, as well as a great stemming vocabulary can be found at http://tartarus.org/martin/PorterStemmer/.
Employing common term-weighting schemes like the tf-idf (term frequency-inverse document frequency) considered in Loughran and McDonald (2011) does not affect the nature of the study’s empirical findings.
It is usual in PCA or similar factor-decomposition applications to only retain the factors/themes that pass certain ‘rules of thumb’. One such ‘rule of thumb’ is to only retain the factors that individually account for 5%, and above, of the variation; another (known as the Guttmann–Kaiser criterion) is to retain any factors with eigenvalue greater than the average of all eigenvalues.
The supplementary use of more than one databases is required for sample size purposes, given the small and fragmented coverage of Hellenic firms by any one database in isolation. In a few cases, values for our variables employed had to be manually collected from the annual reports.
References
Adams, C.A. 2002. Factors influencing corporate social and ethical reporting: moving on from extant theories. Accounting, Auditing and Accountability Journal 15: 223–250.
Aguinis, H., and A. Glavas. 2012. What we know and don’t know about corporate social responsibility: A review and research agenda. Journal of Management 38(4): 932–968.
Alotaibi, K.O., and K. Hussainey. 2016. Determinants of CSR disclosure quantity and quality: Evidence from non-financial listed firms in Saudi Arabia. International Journal of Disclosure and Governance 13(4): 364–393.
Ameer, R., and R. Othman. 2012. Sustainability practices and corporate financial performance: A study based on the top global corporations. Journal of Business Ethics 108(1): 61–79.
Antweiler, W., and M.Z. Frank. 2004. Is all that talk just noise? The information content of internet stock message boards. Journal of Finance 59: 1259–1294.
Aupperle, K.E., A.B. Carroll, and J.D. Hatfield. 1985. An empirical examination of the relationship between corporate social responsibility and profitability. Academy of Management Journal 28(2): 446–463.
Bascle, G. 2008. Controlling for endogeneity with instrumental variables in strategic management research. Strategic Organization 6(3): 285–327.
Beatty, R., and J. Ritter. 1986. Investment banking, reputation and underpricing of initial public offerings. Journal of Financial Economics 15: 213–232.
Belal, A. 2001. A study of corporate social disclosures in Bangladesh. Managerial Auditing Journal 16(5): 274–289.
Berry, M.W., S.T. Dumais, and G. O’Brien. 1995. Using linear algebra for intelligent information retrieval. SIAM Review 37(4): 573–595.
Bichta, C. 2003. Corporate socially responsible (CSR) practices in the context of Greek industry. Corporate Social Responsibility and Environmental Management 10(1): 12–24.
Boukus, E. & Rosenberg J. (2006). The information content of FOMC minutes. In: working paper, Yale University.
Brammer, S.J., and S. Pavelin. 2006. Corporate reputation and social performance: The importance of fit. Journal of Management Studies 43: 435–455.
Brown, S., and J.W. Tucker. 2011. Large-sample evidence on firms’ year-over-year MD&A modifications. Journal of Accounting Research 49: 309–346.
Calabretta, G., B. Durisin, and M. Ogliengo. 2011. Uncovering the intellectual structure of research in business ethics: A journey through the history, the classics, and the pillars of Journal of Business Ethics. Journal of Business Ethics 104(4): 499–524.
Campopiano, G., and A. De Massis. 2014. Corporate social responsibility reporting: A content analysis in family and non-family firms. Journal of Business Ethics 129(3): 1–24.
Canary, H.E., and M.M. Jennings. 2008. Principles and influence in codes of ethics: A centering resonance analysis comparing pre-and post-Sarbanes-Oxley codes of ethics. Journal of Business Ethics 80(2): 263–278.
Chymis, A. & Skouloudis, A. (2014). National CSR and institutional conditions: An exploratory study. In: Discussion Paper No. 139, Centre of Planning and Economic Research (KEPE).
Das, S.R. 2014. Text and context: Language analytics in finance. Foundations and Trends in Finance 8: 145–261.
Das, S.R., and M.Y. Chen. 2007. Yahoo! for Amazon: Sentiment extraction from small talk on the Web. Management Science 53: 1375–1388.
Deegan, C., and B. Gordon. 1996. A study of the environmental disclosure practices of Australian corporations. Accounting and Business Research 26(3): 187–199.
Deegan, C., and M. Rankin. 1996. Do Australian companies report environmental news objectively? An analysis of environmental disclosures by firms prosecuted successfully by the Environmental Protection Authority. Accounting, Auditing and Accountability Journal 9(2): 50–67.
Deerwester, S., S.T. Dumais, G.W. Furnas, T.K. Landauer, and R. Harshman. 1990. Indexing by latent semantic analysis. Journal of the American Society for Information Science 41(6): 391–407.
Duriau, V.J., R.K. Reger, and M.D. Pfarrer. 2007. A content analysis of the content analysis literature in organization studies: Research themes, data sources, and methodological refinements. Organizational Research Methods 10(1): 5–34.
Elkington, J. 1997. Cannibals with forks: The triple bottom line of 21st century business. Oxford: Capstone Publishing.
Elkington, J. 2001. The chrysalis economy: How citizen CEOs and corporations can fuse values and value creation. Oxford: Capstone Publishing.
Ellerup Nielsen, A., and C. Thomsen. 2007. Reporting CSR-what and how to say it? Corporate Communications: An International Journal 12(1): 25–40.
Evangelinos, K.I., and A. Skouloudis. 2014. European perspectives on corporate non-financial disclosure: Evidence from the Southeast. International Journal of Disclosure and Governance 11(1): 33–53.
Evangelinos, K.I., A. Skouloudis, I.E. Nikolaou, and W.L. Filho. 2009. An analysis of corporate social responsibility (CSR) and sustainability reporting assessment in the Greek banking sector. In Professionals’ perspectives of corporate social responsibility, ed. S.O. Idowu and W.L. Filho. Berlin: Springer.
Frazier, K.B., R.W. Ingram, and B.M. Tennyson. 1984. A methodology for the analysis of narrative accounting disclosures. Journal of Accounting Research 22: 318–331.
Frostenson, M., S. Helin, and J. Sandström. 2011. Organising corporate responsibility communication through filtration: A study of web communication patterns in Swedish retail. Journal of Business Ethics 100(1): 31–43.
Gao, Y. 2011. CSR in an emerging country: A content analysis of CSR reports of listed companies. Baltic Journal of Management 6(2): 263–291.
Garcia-Castro, R., M.A. Ariño, and M.A. Canela. 2010. Does social performance really lead to financial performance? Accounting for endogeneity. Journal of Business Ethics 92(1): 107–126.
Giannarakis, G., and N. Litinas. 2011. Corporate social responsibility performance in the Greek telecommunication sector. Strategic Change 20(1–2): 73–84.
Golub, G.H., and C. Reinsch. 1970. Singular value decomposition and least squares solutions. Numerische Mathematik 14(5): 403–420.
Grewal, D., R. Krishnan, J. Baker, and N. Borin. 1998. The effect of store name, brand name and price discounts on consumers evaluations and purchase intentions. Journal of Retailing 74(3): 331–352.
Griffin, J.J., and J.F. Mahon. 1997. The corporate social performance and corporate financial performance debate: Twenty five years of incomparable research. Business and Society 36(1): 5–31.
Grougiou, V., E. Dedoulis, and S. Leventis. 2016. Corporate social responsibility reporting and organizational stigma: The case of “sin” industries. Journal of Business Research 69(2): 905–914.
Haniffa, R.M., and T.E. Cooke. 2005. The impact of culture and governance on corporate social reporting. Journal of Accounting and Public Policy 24(5): 391–430.
Heckman, J. 1979. Sample selection bias as a specification error. Econometrica 47: 153–161.
Herzig, C., and J. Moon. 2013. Discourses on corporate social ir/responsibility in the financial sector. Journal of Business Research 66(10): 1870–1880.
Higgins, C., M.J. Milne, and B. van Gramberg. 2015. The uptake of sustainability reporting in Australia. Journal of Business Ethics 129(2): 1–24.
Huang, A, Lehavy, R., Zang, A. & Zheng, R. (2015). Analyst information discovery and interpretation roles: A topic modeling approach. In: Working paper, University of Michigan.
Jahdi, K.S., and G. Acikdilli. 2009. Marketing communications and corporate social responsibility (CSR): Marriage of convenience or shotgun wedding? Journal of Business Ethics 88(1): 103–113.
Kaptein, M., and J. Wempe. 2002. The balanced company: A corporate integrity approach. Oxford: Oxford University Press.
Kearney, C., and S. Liu. 2014. Textual sentiment in finance: A survey of methods and models. International Review of Financial Analysis 33: 171–185.
Landauer, T.K., P.W. Foltz, and D. Laham. 1998. An introduction to latent semantic analysis. Discourse Processes 25(2–3): 259–284.
Lang, M., and L. Stice-Lawrence. 2015. Textual analysis and international financial reporting: Large sample evidence. Journal of Accounting and Economics 60: 110–135.
Li, F. 2008. Annual report readability, current earnings, and earnings persistence. Journal of Accounting and Economics 45(2–3): 221–247.
Li, F. 2010. Textual analysis of corporate disclosures: A survey of the literature. Journal of Accounting Literature 29: 143–165.
Lock, I., and P. Seele. 2015. Quantitative content analysis as a method for business ethics research. Business Ethics: A European Review 24(S1): S24–S40.
Loughran, T., and B. McDonald. 2011. When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. Journal of Finance 66(1): 35–65.
Loughran, T., and B. McDonald. 2016. Textual analysis in accounting and finance: A survey. Journal of Accounting Research 54(4): 1187–1230.
Lucca, D. & Trebbi, F. (2009), Measuring central bank communication: An automated approach with application to FOMC statements, N.B.E.R. In: Working Paper 15367, Cambridge.
Ma, Z., D. Liang, K.H. Yu, and Y. Lee. 2012. Most cited business ethics publications: Mapping the intellectual structure of business ethics studies in 2001–2008. Business Ethics: A European Review 21(3): 286–297.
Mahadeo, J.D., V. Oogarah-Hanuman, and T. Soobaroyen. 2011. A longitudinal study of corporate social disclosures in a developing economy. Journal of Business Ethics 104(4): 545–558.
Magerman, T., B. Van Looy, and X. Song. 2010. Exploring the feasibility and accuracy of latent semantic analysis based text mining techniques to detect similarity between patent documents and scientific publications. Scientometrics 82(2): 289–306.
Malone, D., and R.W. Roberts. 1996. Public interest reports as medium for corporate disclosure: the case of general motors. Journal of Business Ethics 15: 759–771.
Mazis, P., and A.E. Tsekrekos. 2017. Latent semantic analysis of the FOMC statements. Review of Accounting and Finance 16(2): 179–217.
McGuire, J.B., A. Sundgren, and T. Schneeweis. 1988. Corporate social responsibility and firm financial performance. Academy of Management Journal 31(4): 854–872.
Metaxas, T., and M. Tsavdaridou. 2013. CSR in metallurgy sector in Greece: A content analysis. Resources Policy 38(3): 295–309.
Orlitzky, M., F.L. Schmidt, and S.L. Rynes. 2003. Corporate social and financial performance: A meta-analysis. Organization Studies 24: 403–441.
Othman, R., and R. Ameer. 2009. Corporate social and environmental reporting: Where are we heading? A survey of the literature, International Journal of Disclosure and Governance 6(4): 298–320.
Panayiotou, N.A., K.G. Aravossis, and P. Moschou. 2009. Greece: A comparative study of CSR reports. In Global practices of corporate social responsibility, ed. S.O. Idowu and W.L. Filho. Berlin: Springer.
Parsa, S., and R. Kouhy. 2008. Social reporting by companies listed on the alternative investment market. Journal of Business Ethics 79(3): 345–360.
Paul, K., E. Cobas, R. Ceron, M. Frithiof, A. Maass, I. Navarro, L. Palmer, L. Serrano, and L.Z. Deaton. 2006. Corporate social reporting in Mexico. Journal of Corporate Citizenship 22: 67–80.
Peloza, J. 2009. The challenge of measuring financial impacts from investments in corporate social performance. Journal of Management 35: 1518–1541.
Popping, R. 2000. Computer-assisted text analysis. London: Sage.
Porter, M. 1980. An algorithm for suffix stripping. Program 14(3): 130–137.
Riffe, D., S. Lacy, and F. Fico. 1998. Analyzing media messages: Using quantitative content analysis in research. Mahwah: Lawrence Erlbaum Associates.
Saeidi, S.P., S. Sofian, P. Saeidi, S.P. Saeidi, and S.A. Saaeidi. 2015. How does corporate social responsibility contribute to firm financial performance? The mediating role of competitive advantage, reputation, and customer satisfaction. Journal of Business Research 68(2): 341–350.
Sahinidis, A.G., and A. Kavoura. 2014. Exploring corporate social responsibility practices of Greek companies. Zeszyty Naukowe Małopolskiej Wyższej Szkoły Ekonomicznej w Tarnowie 25(2): 185–193.
Satta, G., F. Parola, G. Profumo, and L. Penco. 2015. Corporate governance and the quality of voluntary disclosure: Evidence from medium-sized listed firms. International Journal of Disclosure and Governance 12(2): 144–166.
Sillanpaa, M. 1998. The Body Shop values report: Towards integrated stakeholder auditing. Journal of Business Ethics 17(1): 443–456.
Simpson, W.G., and T. Kohers. 2002. The link between corporate social and financial performance: Evidence from the banking industry. Journal of Business Ethics 35(2): 97–109.
Taneja, S.S., P.K. Taneja, and R.K. Gupta. 2011. Researches in corporate social responsibility: A review of shifting focus, paradigms, and methodologies. Journal of Business Ethics 101(3): 343–364.
Tetlock, P.C. 2007. Giving content to investor sentiment: The role of media in the stock market. Journal of Finance 62(3): 1139–1168.
Thompson, P., and Z. Zakaria. 2004. Corporate social responsibility reporting in Malaysia: Progress and prospects. Journal of Corporate Citizenship 13: 125–136.
Vong, F., and I.A. Wong. 2013. Corporate and social performance links in the gaming industry. Journal of Business Research 66(9): 1674–1681.
Vuontisjärvi, T. 2006. Corporate social reporting in the European context and human resource disclosures: An analysis of Finnish companies. Journal of Business Ethics 69: 331–354.
Waddock, S.A., and S.B. Graves. 1997. The corporate social performance-financial performance link. Strategic Management Journal 18(4): 303–319.
Wall, M.E., A. Rechtsteiner, and L.M. Rocha. 2003. Singular value decomposition and principal component analysis. In A practical approach to microarray data analysis, ed. D.P. Berrar, W. Dubitzky, and M. Granzow. Norwell: Kluwer.
Wallage, P. 2000. Assurance on sustainability reporting: An auditor’s view. Auditing 19: 53–65.
Wanderley, L.S.O., R. Lucian, F. Farache, and J.M. de Sousa Filho. 2008. CSR information disclosure on the web: A context-based approach analysing the influence of country of origin and industry sector. Journal of Business Ethics 82(2): 369–378.
Wang, D.H.M., P.H. Chen, T.H.K. Yu, and C.Y. Hsiao. 2015. The effects of corporate social responsibility on brand equity and firm performance. Journal of Business Research 68(11): 2232–2236.
Young, L., and S. Soroka. 2011. Affective news: The automated coding of sentiment in political texts. Political Communication 29(2): 205–231.
Zhao, M. 2012. CSR-based political legitimacy strategy: Managing the state by doing good in China and Russia. Journal of Business Ethics 111(4): 439–460.
Acknowledgements
We are grateful to Professor Michael Alles (the editor) for insightful comments and suggestions that have greatly improved the paper. We are also grateful to Fotios Kitsios for providing detailed comments on an earlier version of the paper and to Panagiotis Mazis for discussions and suggestions on earlier drafts. The paper has benefited from comments and suggestions by participants of the 14th annual conference of the Hellenic Finance and Accounting Association (HFAA) and of the 2nd FSTEP conference at the University of Macedonia. The last author gratefully acknowledges the financial support provided by the Basic Research Funding Program of the A.U.E.B. research center (project EP–1990–01) and by project EP–1688–01 of the A.U.E.B. research center. Any errors are the authors’ sole responsibility.
Author information
Authors and Affiliations
Corresponding author
Appendix 1: Example of the document filtering process
Appendix 1: Example of the document filtering process
This Appendix demonstrates the CSR reports’ text preprocessing that is discussed in "Formation of the corpus and text preprocessing" section of the text, by using the 2009 report by Alpha Bank as an example.
-
1.
Raw data (edited exert from Alpha Bank’s CSR report 2009)
The Bank’s guiding principles are integrity, honesty, fairness, and independence. With these values firmly in mind, we consistently strive to ensure that our transparency and operations support the comprehensive implementation of the financial sector regulatory framework.
-
2.
Remove formatting and delete stop words (stop words seem marked-up)
The Bank’s guiding principles are integrity, honesty, fairness, and independence. With these values firmly in mind, we consistently strive to ensure that our transparency and operations support the comprehensive implementation of the financial sector regulatory framework.
-
3.
Lemmatization
Guide principle integrity honesty fairness independence value mind strive ensure transparency operation support comprehensive implementation financial sector regulatory framework
-
4.
Stemming and list the unique words in alphabetic order
Comprehens ensur fair finance framework guid honesti implement independ integr mind oper principl regulatori sector strive support transpar valu
Rights and permissions
About this article
Cite this article
Kountouri, I., Manousakis, E. & Tsekrekos, A.E. Latent semantic analysis of corporate social responsibility reports (with an application to Hellenic firms). Int J Discl Gov 16, 1–19 (2019). https://doi.org/10.1057/s41310-018-0053-z
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1057/s41310-018-0053-z