Business demands for processing unstructured textual data – text mining techniques for companies to implement

Denitsa Zhecheva () and Nayden Nenkov ()
Additional contact information
Denitsa Zhecheva: Konstantin Preslavsky University of Shumen, Shumen, Bulgaria
Nayden Nenkov: Konstantin Preslavsky University of Shumen, Shumen, Bulgaria

Access Journal, 2022, vol. 3, issue 2, 107-120

Abstract: The rapid development of technology has caused a pervasive change in the way people and businesses live. Making sound business decisions is unthinkable without processing a large amount of data (publicly available and collected on the basis of problems) with high accuracy and quality. The importance of unstructured data acquires various sources is growing. Of particular value is the continuous flow of textual information that is generated every minute around the world in a different form (unstructured textual data). This is also the subject of this article. The aim of the article is to provide an analytical overview of the main methods of word processing that are applicable for pragmatic analysis of information flows from companies, such as: extraction, summarization, grouping and categorization of text. Some methodologies are based on NLP (Natural Language Processing), others on Bayesian logic and statistical theory and practice. From the review of various publications on the topic, conclusions are proposed for their practical applicability. This allows for an objective choice of appropriate tools for processing unstructured information and business intelligence. The results of the study can be successfully used to improve managerial decision-making, improve the quality of work of employees and reduce errors in overall marketing planning.

Keywords: clustering; unstructured textual data; business intelligence; NLP (Natural Language Processing); text mining; text extraction; text summarization; text categorization; text retrieval (search for similar items in EconPapers)
JEL-codes: C15 C81 C82 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journal.access-bg.org/journalfiles/journal ... red_textual_data.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aip:access:v:3:y:2022:i:2:p:107-120

DOI: 10.46656/access.2022.3.2(2)

Access Statistics for this article

More articles in Access Journal from Access Press Publishing House
Bibliographic data for series maintained by Mariana Petrova ().