μXL: Explainable Lead Generation with Microservices and Hypothetical Answers

Luís Cruz-Filipe, Sofia Kostopoulou, Fabrizio Montesi, Jonas Vistrup [2023].
In proceedings of ESOCC 2023, pp. 3-18.

Abstract

Lead generation refers to the identification of potential topics (the 'leads') of importance for journalists to report on. In this paper we present a new lead generation tool based on a microservice architecture, which includes a component of explainable AI. The lead generation tool collects and stores historical and real-time data from a web source, like Google Trends, and generates current and future leads. These leads are produced by an engine for hypothetical reasoning based on logical rules, which is a novel implementation of a recent theory. Finally, the leads are displayed on a web interface for end users, in particular journalists. This interface provides information on why a specific topic is or may become a lead, assisting journalists in deciding where to focus their attention. We carry out an empirical evaluation of the performance of our tool.

Links

doi.org

Additional notes

None

Cite (BibTeX)

Click to expand

@inproceedings{DBLP:conf/esocc/CruzFilipeKMV23,
  author       = {Lu{\'{\i}}s Cruz{-}Filipe and
                  Sofia Kostopoulou and
                  Fabrizio Montesi and
                  Jonas Vistrup},
  editor       = {George A. Papadopoulos and
                  Florian Rademacher and
                  Jacopo Soldani},
  title        = {{\(\mu\)}XL: Explainable Lead Generation with Microservices and Hypothetical
                  Answers},
  booktitle    = {Service-Oriented and Cloud Computing - 10th {IFIP} {WG} 6.12 European
                  Conference, {ESOCC} 2023, Larnaca, Cyprus, October 24-25, 2023, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {14183},
  pages        = {3--18},
  publisher    = {Springer},
  year         = {2023},
  url          = {https://doi.org/10.1007/978-3-031-46235-1\_1},
  doi          = {10.1007/978-3-031-46235-1\_1},
  timestamp    = {Thu, 09 Nov 2023 21:13:04 +0100},
  biburl       = {https://dblp.org/rec/conf/esocc/CruzFilipeKMV23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

A PDF is available (possibly a preprint):

Some data from DBLP and Crossref.