Abstract
This paper gives an outline of eRisk 2021, the CLEF conference’s fifth edition of this lab. The main goal of eRisk is to explore issues of evaluation methodology, effectiveness metrics and other processes related to early risk detection. Early alerting models may be used in a variety of situations, including those involving health and safety. This edition of eRisk had three tasks. The first task focused on early detecting signs of pathological gambling. The second challenge was to spot early signs of self-harm. The third required participants to fill out a depression questionnaire (automatically, based on user writings on social media).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
computed with respect to the positive class.
- 3.
Observe that Sadeque et al. (see [17], pg 497) computed the latency for all users such that \(g_u=1\). We argue that latency should be computed only for the true positives. The false negatives (\(g_u=1\), \(d_u=0\)) are not detected by the system and, therefore, they would not generate an alert.
- 4.
Again, we adopt Sadeque et al.’s proposal but we estimate latency only over the true positives.
- 5.
In the evaluation we set p to 0.0078, a setting obtained from the eRisk 2017 collection.
- 6.
- 7.
In the two questions (#16 and #18) that have seven possible answers \(\{0, 1a,\) 1b, 2a, 2b, 3a \(, 3b\}\) the pairs (1a, 1b), (2a, 2b), (3a, 3b) are considered equivalent because they reflect the same depression level. As a consequence, the difference between 3b and 0 is equal to 3 (and the difference between 1a and 1b is equal to 0).
References
Abbott, M.: The epidemiology and impact of gambling disorder and other gambling-related harm. In: WHO Forum on Alcohol, Drugs and Addictive Behaviours, Geneva, Switzerland (2017)
Beck, A.T., Ward, C.H., Mendelson, M., Mock, J., Erbaugh, J.: An inventory for measuring depression. JAMA Psychiatry 4(6), 561–571 (1961)
Losada, D.E., Crestani, F.: A test collection for research on depression and language use. In: Fuhr, N., et al. (eds.) CLEF 2016. LNCS, vol. 9822, pp. 28–39. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44564-9_3
Losada, D.E., Crestani, F., Parapar, J.: eRISK 2017: CLEF lab on early risk prediction on the internet: experimental foundations. In: Jones, G.J.F., et al. (eds.) CLEF 2017. LNCS, vol. 10456, pp. 346–360. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-65813-1_30
Losada, D.E., Crestani, F., Parapar, J.: eRisk 2017: CLEF lab on early risk prediction on the internet: experimental foundations. In: CEUR Proceedings of the Conference and Labs of the Evaluation Forum, CLEF 2017, Dublin, Ireland (2017)
Losada, D.E., Crestani, F., Parapar, J.: Overview of eRisk 2018: early risk prediction on the internet (extended lab overview). In: CEUR Proceedings of the Conference and Labs of the Evaluation Forum, CLEF 2018, Avignon, France (2018)
Losada, D.E., Crestani, F., Parapar, J.: Overview of eRisk: early risk prediction on the internet. In: Bellot, P., et al. (eds.) CLEF 2018. LNCS, vol. 11018, pp. 343–361. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-98932-7_30
Losada, D.E., Crestani, F., Parapar, J.: Early detection of risks on the internet: an exploratory campaign. In: Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., Hiemstra, D. (eds.) ECIR 2019. LNCS, vol. 11438, pp. 259–266. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-15719-7_35
Losada, D.E., Crestani, F., Parapar, J.: Overview of eRisk 2019 early risk prediction on the internet. In: Crestani, F., et al. (eds.) CLEF 2019. LNCS, vol. 11696, pp. 340–357. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28577-7_27
Losada, D.E., Crestani, F., Parapar, J.: Overview of eRisk at CLEF 2019: early risk prediction on the internet (extended overview). In: CEUR Proceedings of the Conference and Labs of the Evaluation Forum, CLEF 2019, Lugano, Switzerland (2019)
Losada, D.E., Crestani, F., Parapar, J.: erisk 2020: self-harm and depression challenges. In: Advances in Information Retrieval - 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, 14–17 April 2020, Proceedings, Part II, pp. 557–563 (2020)
Losada, D.E., Crestani, F., Parapar, J.: Overview of eRisk 2020: early risk prediction on the internet. In: Arampatzis, A., et al. (eds.) CLEF 2020. LNCS, vol. 12260, pp. 272–287. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58219-7_20
Losada, D.E., Crestani, F., Parapar, J.: Overview of erisk at CLEF 2020: early risk prediction on the internet (extended overview). In: Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum, Thessaloniki, Greece, 22–25 September 2020 (2020)
Otero, D., Parapar, J., Barreiro, Á.: Beaver: efficiently building test collections for novel tasks. In: Proceedings of the First Joint Conference of the Information Retrieval Communities in Europe (CIRCLE 2020), Samatan, Gers, France, 6–9 July 2020 (2020)
Otero, D., Parapar, J., Barreiro, Á.: The wisdom of the rankers: a cost-effective method for building pooled test collections without participant systems. In: SAC ’21: The 36th ACM/SIGAPP Symposium on Applied Computing, Virtual Event, Republic of Korea, 22–26 March 2021, pp. 672–680 (2021)
Parapar, J., Martín-Rodilla, P., Losada, D.E., Crestani, F.: erisk 2021: pathological gambling, self-harm and depression challenges. In: Advances in Information Retrieval - 43rd European Conference on IR Research, ECIR 2021, Virtual Event, 28 March–1 April 2021, Proceedings, Part II, pp. 650–656 (2021)
Sadeque, F., Xu, D., Bethard, S.: Measuring the latency of depression detection in social media. In: WSDM, pp. 495–503. ACM (2018)
Trotzek, M., Koitka, S., Friedrich, C.: Utilizing neural networks and linguistic metadata for early detection of depression indications in text sequences. IEEE Trans. Knowl. Data Eng. 32, 588–601 (2018)
Acknowledgements
This work was supported by projects RTI2018-093336-B-C21, RTI2018-093336-B-C22 (Ministerio de Ciencia e Innvovación & ERDF). The first and second authors thank the financial support supplied by the Consellería de Educación, Universidade e Formación Profesional (accreditation 2019–2022 ED431G/01, ED431B 2019/03) and the European Regional Development Fund, which acknowledges the CITIC Research Center in ICT of the University of A Coruña as a Research Center of the Galician University System. The third author also thanks the financial support supplied by the Consellería de Educación, Universidade e Formación Profesional (accreditation 2019–2022 ED431G-2019/04, ED431C 2018/29) and the European Regional Development Fund, which acknowledges the CiTIUS-Research Center in Intelligent Technologies of the University of Santiago de Compostela as a Research Center of the Galician University System.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Parapar, J., Martín-Rodilla, P., Losada, D.E., Crestani, F. (2021). Overview of eRisk 2021: Early Risk Prediction on the Internet. In: Candan, K.S., et al. Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2021. Lecture Notes in Computer Science(), vol 12880. Springer, Cham. https://doi.org/10.1007/978-3-030-85251-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-85251-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85250-4
Online ISBN: 978-3-030-85251-1
eBook Packages: Computer ScienceComputer Science (R0)