Projects / Programmes source: ARIS

Influence of formal and informal corporate communications on capital markets

Research activity

Code Science Field Subfield
5.02.02  Social sciences  Economics  Business sciences 

Code Science Field
S192  Social sciences  Accounting 

Code Science Field
5.02  Social Sciences  Economics and Business 
capital market, analsis of social networks, artificial intelligence, machine learning, sentiment analysis, data mining, financial reports
Evaluation (rules)
source: COBISS
Researchers (13)
no. Code Name and surname Research area Role Period No. of publicationsNo. of publications
1.  37929  Sandra Đurašević    Technical associate  2017 - 2018 
2.  37928  Erna Emrić    Technical associate  2016 
3.  36630  PhD James Foye  Economics  Researcher  2016 - 2018  23 
4.  28291  PhD Petra Kralj Novak  Computer science and informatics  Researcher  2018  130 
5.  08949  PhD Nada Lavrač  Computer science and informatics  Researcher  2016 - 2018  863 
6.  19248  PhD Marko Pahor  Economics  Researcher  2016 - 2018  536 
7.  29539  PhD Vid Podpečan  Computer science and informatics  Researcher  2018  99 
8.  31844  PhD Senja Pollak  Linguistics  Researcher  2016 - 2018  276 
9.  37977  PhD Jasmina Smailović  Computer science and informatics  Researcher  2016 - 2017  40 
10.  36911  PhD Rok Spruk  Economics  Researcher  2017 - 2018  462 
11.  18932  PhD Aljoša Valentinčič  Economics  Head  2016 - 2018  495 
12.  34262  PhD Anže Vavpetič  Computer science and informatics  Researcher  2016 - 2017  30 
13.  23582  PhD Martin Žnidaršič  Computer science and informatics  Researcher  2016 - 2018  163 
Organisations (2)
no. Code Research organisation City Registration number No. of publicationsNo. of publications
1.  0106  Jožef Stefan Institute  Ljubljana  5051606000  88,610 
2.  0584  University of Ljubljana, School of Economics and Business (SEB)  Ljubljana  1626922  41,704 
The goal of our research is to study the importance of informal communications and unregulated parts of annual reports for capital markets. The main goal of financial reporting in the financial system is to ensure high-quality, useful information about the financial position of firms, their performance and changes in their financial position is available (IASB Framework 2015) to a wide range of users, including existing and potential investors, financial institutions, employees, the government, etc. Formal reports contain both strictly regulated, financial sections, as well as unregulated, narrative parts. While formal communications are the subject of academic research, studies are relatively scarce. Our research starts from the hypothesis that informal communications are useful for capital markets, too, and that there is a relation between business performance and linguistic properties of unregulated parts of annual reports. However, formal communications with capital markets – be it in the form of regulated financial sections and unregulated parts of annual reports – do have weaknesses: direct and indirect costs, strict timelines (leading to a reporting delay between economic events and reporting dates), important information is omitted from these reports due to some properties of formal rules of financial reporting (even though they are priced by the market). We thus expand our research to include informal forms of communications such as posts on social networks and financial blogs. These focus on the short-term aspects of our study. On the long-(er)-term side, we will focus on the explanatory and predictive power of narratives in annual reports. We will use the methods of artificial intelligence - classification models, predictive machine learning. We will focus on transparent models that enable interpretation by domain experts. In data model construction the methods will use frequency based features and sentiment analysis (crucial for informal communication on social media), as well as more complex linguistic markers, such as referential vagueness (expressed by e.g. passive constructions and nominalisation), pronouns, adjective superlatives, specific collocations, etc. that are important especially in unregulated textual annual reports. Our research is innovative precisely because it relates linguistic properties and machine learning to capital markets and then relates these findings to the formal financial reporting system, to unregulated parts of formal reports and to other informal forms of communication. Despite the importance of this information to capital markets, there are relatively few academic studies in this area and several take very partial approaches. If this information is important for the capital markets (investors), they should be reflected in share prices, lower variability of share prices and thus lower risk, higher volume of trading, etc., which all leads to lower costs of capital, increases the amount of profitable investment opportunities for firms, ultimately leading to higher GDP growth. Our research has implications for a large part of the economic system. The size of EU capital markets is 52% of GDP and the size of debt-securities markets 79% of GDP (ECB 2015). Our research aims to overcome uncertainty in capital markets and increase the quality of information available to investors. The key outcome of this is lower cost of capital, which increases firms’ investment, and more investments leads to higher economic growth (gross domestic product).
Significance for science
Our research will contribute to the development of sciences in the following fields:   - economic and business sciences: i) modelling the relation between capital markets on the one hand and the system of formal financial reporting and informal communications; determining the market value of firms; information content of informal communications; ii) accounting: relevance of accounting data, relevance of narratives in annual reports; iii) auditing: is it possible to audit informal communications; iv) economics: functioning of capital markets, regulation.   - computer science and natural language processing: i) linguistically enriched sentiment analysis models: improvement of models of informal communication of Twitter, new development of sentiment analysis on financial blogs, modeling of long-term effects of informal communication; ii) natural language processing: development of extractors of linguistic features (important also for other text mining applications), iii) data mining on texts of annual reports iv) mining of heterogeneous data: predictive models by combining information from heterogeneous sources (financial data, informal communication, textual unregulated parts of annual reports)   - discourse analysis: i) new hypotheses on reporting on positive and negative financial outcomes; ii) comparison of domain informal (financial tweets and blogs) and formal (annual reports) language use; iii) extraction of domain terminology: domain terminology and collocation frequency lists can be used for financial discourse analysis (translation, teaching of domain terminology, computer science applications).
Significance for the country
The results of our work are directly important for: - firms that obtain capital for growth on open capital markets - all elements of our research have consequences for the cost of capital that serves as an input to investment decisions of these firms via the net present value of investment. Ultimately, this is reflected in gross domestic product (GDP) growth. Informal communications are one of the elements that can reduce the cost of capital; - companies from the field of ICT (such as semantic web, information mining, sentiment analysis): companies can integrate the developed technologies in their products and increase their competitiveness (e.g. JSI already collaborates with company Gama Systems in the domain of sentiment analysis). - at the level of countries(government) and EU our results are important for: regulation of the formal system of financial reporting (development of accounting standards, auditing, audit oversight, capital market regulation) and consequently the entire financial system where information we study are used as a basis for decision making.
Most important scientific results Interim report, final report
Most important socioeconomically and culturally relevant results Interim report, final report
Views history