We present a comprehensive framework for managing reports sent to the local government by citizens through wellknown instant messaging apps. It leverages a combined use of Web systems and automated bots, based on Machine Learning techniques. This project has been developed in collaboration with the local administration of Montecchio Emilia (Italy). The results show that an automatic classification system of this kind can reach very good levels of accuracy, also above 90%.

Automatic processing and classification of citizens’ reports / Angiani, G.; Mordonini, M.; Pietroni, U.; Fornacciari, P.; Lombardo, G.; Tomaiuolo, M.. - (2018), pp. 310-311. (Intervento presentato al convegno 4th EAI International Conference on Smart Objects and Technologies for Social Good, GOODTECHS 2018 tenutosi a ita nel 2018) [10.1145/3284869.3284930].

Automatic processing and classification of citizens’ reports

Angiani G.;Mordonini M.;Pietroni U.;Fornacciari P.;Lombardo G.;Tomaiuolo M.
2018-01-01

Abstract

We present a comprehensive framework for managing reports sent to the local government by citizens through wellknown instant messaging apps. It leverages a combined use of Web systems and automated bots, based on Machine Learning techniques. This project has been developed in collaboration with the local administration of Montecchio Emilia (Italy). The results show that an automatic classification system of this kind can reach very good levels of accuracy, also above 90%.
2018
9781450365819
Automatic processing and classification of citizens’ reports / Angiani, G.; Mordonini, M.; Pietroni, U.; Fornacciari, P.; Lombardo, G.; Tomaiuolo, M.. - (2018), pp. 310-311. (Intervento presentato al convegno 4th EAI International Conference on Smart Objects and Technologies for Social Good, GOODTECHS 2018 tenutosi a ita nel 2018) [10.1145/3284869.3284930].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11381/2867072
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
social impact