Details
| Original language | English |
|---|---|
| Pages (from-to) | 339-364 |
| Number of pages | 26 |
| Journal | International Journal on Digital Libraries |
| Volume | 22 |
| Issue number | 4 |
| Early online date | 9 Oct 2021 |
| Publication status | Published - Dec 2021 |
Abstract
Inferring the magnitude and occurrence of real-world events from natural language text is a crucial task in various domains. Particularly in the domain of public health, the state-of-the-art document and token centric event detection approaches have not kept the pace with the growing need for more robust event detection in public health. In this paper, we propose UPHED, a unified approach, which combines both the document and token centric event detection techniques in an unsupervised manner such that events which are: rare (aperiodic); reoccurring (periodic) can be detected using a generative model for the domain of public health. We evaluate the efficiency of our approach as well as its effectiveness for two real-world case studies with respect to the quality of document clusters. Our results show that we are able to achieve a precision of 60% and a recall of 71% analyzed using manually annotated real-world data. Finally, we also make a comparative analysis of our work with the well-established rule-based system of MedISys and find that UPHED can be used in a cooperative way with MedISys to not only detect similar anomalies, but can also deliver more information about the specific outbreak of reported diseases.
Keywords
- Clustering, Event-based epidemic intelligence, Retrospective public health event detection
ASJC Scopus subject areas
- Social Sciences(all)
- Library and Information Sciences
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International Journal on Digital Libraries, Vol. 22, No. 4, 12.2021, p. 339-364.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Unified approach to retrospective event detection for event- based epidemic intelligence
AU - Fisichella, Marco
N1 - Funding Information: The work was partially funded by the European Commission for the eXplainable Artificial Intelligence in healthcare Management (xAIM) project, agreement No INEA/CEF/ICT/A2020/2276680.
PY - 2021/12
Y1 - 2021/12
N2 - Inferring the magnitude and occurrence of real-world events from natural language text is a crucial task in various domains. Particularly in the domain of public health, the state-of-the-art document and token centric event detection approaches have not kept the pace with the growing need for more robust event detection in public health. In this paper, we propose UPHED, a unified approach, which combines both the document and token centric event detection techniques in an unsupervised manner such that events which are: rare (aperiodic); reoccurring (periodic) can be detected using a generative model for the domain of public health. We evaluate the efficiency of our approach as well as its effectiveness for two real-world case studies with respect to the quality of document clusters. Our results show that we are able to achieve a precision of 60% and a recall of 71% analyzed using manually annotated real-world data. Finally, we also make a comparative analysis of our work with the well-established rule-based system of MedISys and find that UPHED can be used in a cooperative way with MedISys to not only detect similar anomalies, but can also deliver more information about the specific outbreak of reported diseases.
AB - Inferring the magnitude and occurrence of real-world events from natural language text is a crucial task in various domains. Particularly in the domain of public health, the state-of-the-art document and token centric event detection approaches have not kept the pace with the growing need for more robust event detection in public health. In this paper, we propose UPHED, a unified approach, which combines both the document and token centric event detection techniques in an unsupervised manner such that events which are: rare (aperiodic); reoccurring (periodic) can be detected using a generative model for the domain of public health. We evaluate the efficiency of our approach as well as its effectiveness for two real-world case studies with respect to the quality of document clusters. Our results show that we are able to achieve a precision of 60% and a recall of 71% analyzed using manually annotated real-world data. Finally, we also make a comparative analysis of our work with the well-established rule-based system of MedISys and find that UPHED can be used in a cooperative way with MedISys to not only detect similar anomalies, but can also deliver more information about the specific outbreak of reported diseases.
KW - Clustering
KW - Event-based epidemic intelligence
KW - Retrospective public health event detection
UR - http://www.scopus.com/inward/record.url?scp=85116791341&partnerID=8YFLogxK
U2 - 10.1007/s00799-021-00308-9
DO - 10.1007/s00799-021-00308-9
M3 - Article
AN - SCOPUS:85116791341
VL - 22
SP - 339
EP - 364
JO - International Journal on Digital Libraries
JF - International Journal on Digital Libraries
SN - 1432-5012
IS - 4
ER -