A systematic mapping study on agent mining

ABSTRACT

Over the past two decades, many studies have been published in diverse fields of application combining agent abilities (knowledge processing, communication, learning, mobility, etc.) and data mining approaches (clustering, decision trees, ontologies, etc.). We performed a systematic mapping study to quantitatively analyse these contributions about agent mining. We determined that most of the publications were in the field of data mining using agent systems to collect or mine the data. Some used data mining solutions to improve agent behaviour, and very few publications integrated both agent and mining approaches. In the latter case, most were published in the last few years, which highlights the advances in research integrating agents and mining approaches.

KEYWORDS:

• Agent
• data mining
• knowledge discovery
• agent mining
• systematic mapping study (SMS)

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. even if the term ‘intelligent system’ is still used but covers a larger area than the field of agents.

2. See the study by Cao (2017a) for an overview of data science.

3. http://www.scopus.com.

4. http://www.isiknowledge.com.

5. https://github.com/JabRef/jabref.

6. We have excluded books and book chapters that are not from conference proceedings because of the difficulty in determining whether they were peer-reviewed or not.

7. We used the Fleiss Kappa for global score of the three readers.

8. Set of analysed papers: http://doi.org/10.13140/RG.2.2.18224.17920

9. We recall that the selection in the databases was performed on 16 July 2020. Several other studies will unquestionably appear up until the end of the year. In addition, it is common for proceedings to be published with a certain delay after the conference.

10. FIPA ACL Message Structure Specification: http://www.fipa.org/specs/fipa00061/SC00061G.pdf.