KPTopic: A Topic Generator Built on the Semantic Network of Key Parts of Speech

Peng A. Yang (), Juho Pesonen, Heli Hallikainen and Andrei Kirilenko
Additional contact information
Peng A. Yang: University of Eastern Finland, Business School
Juho Pesonen: University of Eastern Finland, Business School
Heli Hallikainen: University of Eastern Finland, Business School
Andrei Kirilenko: University of Florida, Department of Tourism, Hospitality and Event Management

Chapter 2 in Information and Communication Technologies in Tourism 2026, 2026, pp 17-30 from Springer

Abstract: Abstract This paper introduces KPTopic, a graph-based topic generator specifically designed for tourism research. By leveraging advanced natural language processing techniques, KPTopic extends conventional topic modeling methods through the construction of a semantic network that integrates key parts of speech, including adjectives, verbs, and nouns, to capture rich semantic relationships within textual data. The model further enhances contextual understanding by incorporating extensive noun-to-noun associations and metadata such as visit dates and business types. Applied to 11,729 TripAdvisor reviews of Finland, KPTopic produces coherent and interpretable topics that reflect tourists’ perceptions. Its robustness to noisy data, minimal preprocessing requirements, and ability to incorporate emojis as emotional cues make it particularly suitable for analyzing textual content. In addition, KPTopic can be complemented with GenAI tools to improve interpretability and by addressing the limitations of black-box models.

Keywords: Topic modeling; KPTopic; GenAI; Semantic network analysis; Finland; Part of speech (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:spr:prbchp:978-3-032-23925-9_2

Ordering information: This item can be ordered from
http://www.springer.com/9783032239259

DOI: 10.1007/978-3-032-23925-9_2

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().