Predicting the Individual Mood Level based on Diary Data

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Standard

Predicting the Individual Mood Level based on Diary Data. / Bremer, Vincent; Becker, Dennis; Funk, Burkhardt et al.
Proceedings of the 25th European Conference on Information Systems, ECIS 2017. AIS eLibrary, 2017. p. 1161-1177 (Proceedings of the 25th European Conference on Information Systems, ECIS 2017).

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Harvard

Bremer, V, Becker, D, Funk, B & Lehr, D 2017, Predicting the Individual Mood Level based on Diary Data. in Proceedings of the 25th European Conference on Information Systems, ECIS 2017. Proceedings of the 25th European Conference on Information Systems, ECIS 2017, AIS eLibrary, pp. 1161-1177, 25th European Conference on Information Systems - ECIS 2017, Guimaraes, Portugal, 05.06.17. <http://aisel.aisnet.org/ecis2017_rp/75/>

APA

Bremer, V., Becker, D., Funk, B., & Lehr, D. (2017). Predicting the Individual Mood Level based on Diary Data. In Proceedings of the 25th European Conference on Information Systems, ECIS 2017 (pp. 1161-1177). (Proceedings of the 25th European Conference on Information Systems, ECIS 2017). AIS eLibrary. http://aisel.aisnet.org/ecis2017_rp/75/

Vancouver

Bremer V, Becker D, Funk B, Lehr D. Predicting the Individual Mood Level based on Diary Data. In Proceedings of the 25th European Conference on Information Systems, ECIS 2017. AIS eLibrary. 2017. p. 1161-1177. (Proceedings of the 25th European Conference on Information Systems, ECIS 2017).

Bibtex

@inbook{b4172b2ccd3a4b2aaac024959089aeb0,
title = "Predicting the Individual Mood Level based on Diary Data",
abstract = "Understanding mood changes of individuals with depressive disorders is crucial in order to guide personalized therapeutic interventions. Based on diary data, in which clients of an online depression treatment report their activities as free text, we categorize these activities and predict the mood level of clients. Weapply a bag-of-words text-mining approach for activity categorization and explore recurrent neuronal networks to support this task. Using the identified activities, we develop partial ordered logit models with varying levels of heterogeneity among clients to predict their mood. We estimate the parameters of these models by employing Markov Chain Monte Carlo techniques and compare the models regarding their predictive performance. Therefore, by combining text-mining and Bayesian estimation techniques, we apply a two-stage analysis approach in order to reveal relationships between various activity categories and the individual mood level. Our findings indicate that the mood level is influenced negatively when participants report about sickness or rumination. Social activities have a positive influence on the mood.By understanding the influences of daily activities on the individual mood level, we hope to improve the efficacy of online behavior therapy, provide support in the context of clinical decision-making, and contribute to the development of personalized interventions.",
keywords = "Business informatics, Decision Support, E-mental health, Text-Mining, Bayesian Method, Personalized Treatments",
author = "Vincent Bremer and Dennis Becker and Burkhardt Funk and Dirk Lehr",
note = "Publisher Copyright: {\textcopyright} 2017 Proceedings of the 25th European Conference on Information Systems, ECIS 2017. All rights reserved.; 25th European Conference on Information Systems - ECIS 2017, ECIS 2017 ; Conference date: 05-06-2017 Through 10-06-2017",
year = "2017",
month = jun,
language = "English",
isbn = "978-989-20-7655-3",
series = "Proceedings of the 25th European Conference on Information Systems, ECIS 2017",
publisher = "AIS eLibrary",
pages = "1161--1177",
booktitle = "Proceedings of the 25th European Conference on Information Systems, ECIS 2017",
address = "United States",
url = "https://aisel.aisnet.org/ecis2017/",

}

RIS

TY - CHAP

T1 - Predicting the Individual Mood Level based on Diary Data

AU - Bremer, Vincent

AU - Becker, Dennis

AU - Funk, Burkhardt

AU - Lehr, Dirk

N1 - Conference code: 25

PY - 2017/6

Y1 - 2017/6

N2 - Understanding mood changes of individuals with depressive disorders is crucial in order to guide personalized therapeutic interventions. Based on diary data, in which clients of an online depression treatment report their activities as free text, we categorize these activities and predict the mood level of clients. Weapply a bag-of-words text-mining approach for activity categorization and explore recurrent neuronal networks to support this task. Using the identified activities, we develop partial ordered logit models with varying levels of heterogeneity among clients to predict their mood. We estimate the parameters of these models by employing Markov Chain Monte Carlo techniques and compare the models regarding their predictive performance. Therefore, by combining text-mining and Bayesian estimation techniques, we apply a two-stage analysis approach in order to reveal relationships between various activity categories and the individual mood level. Our findings indicate that the mood level is influenced negatively when participants report about sickness or rumination. Social activities have a positive influence on the mood.By understanding the influences of daily activities on the individual mood level, we hope to improve the efficacy of online behavior therapy, provide support in the context of clinical decision-making, and contribute to the development of personalized interventions.

AB - Understanding mood changes of individuals with depressive disorders is crucial in order to guide personalized therapeutic interventions. Based on diary data, in which clients of an online depression treatment report their activities as free text, we categorize these activities and predict the mood level of clients. Weapply a bag-of-words text-mining approach for activity categorization and explore recurrent neuronal networks to support this task. Using the identified activities, we develop partial ordered logit models with varying levels of heterogeneity among clients to predict their mood. We estimate the parameters of these models by employing Markov Chain Monte Carlo techniques and compare the models regarding their predictive performance. Therefore, by combining text-mining and Bayesian estimation techniques, we apply a two-stage analysis approach in order to reveal relationships between various activity categories and the individual mood level. Our findings indicate that the mood level is influenced negatively when participants report about sickness or rumination. Social activities have a positive influence on the mood.By understanding the influences of daily activities on the individual mood level, we hope to improve the efficacy of online behavior therapy, provide support in the context of clinical decision-making, and contribute to the development of personalized interventions.

KW - Business informatics

KW - Decision Support

KW - E-mental health

KW - Text-Mining

KW - Bayesian Method

KW - Personalized Treatments

UR - http://www.scopus.com/inward/record.url?scp=85045636125&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/e76a3afb-4841-3f45-b4db-535a01fe2af8/

M3 - Article in conference proceedings

SN - 978-989-20-7655-3

T3 - Proceedings of the 25th European Conference on Information Systems, ECIS 2017

SP - 1161

EP - 1177

BT - Proceedings of the 25th European Conference on Information Systems, ECIS 2017

PB - AIS eLibrary

T2 - 25th European Conference on Information Systems - ECIS 2017

Y2 - 5 June 2017 through 10 June 2017

ER -

Links

Recently viewed

Publications

  1. Archives
  2. Working memory capacity and narrative task performance
  3. Continued logarithm representation of real numbers
  4. Interplays between relational and instrumental values
  5. Performance Saga: Interview 06
  6. Multiple
  7. Passive Rotation Compensation in Parallel Kinematics Using Quaternions
  8. Study of non-linear systems
  9. An Experimental Approach to the Optimization of Customer Information at the Point of Sale
  10. Development and validation of chemometrics-assisted spectrophotometry and liquid chromatography methods for the simultaneous determination of the active ingredients in two multicomponent mixtures containing chlorpheniramine maleate and phenylpropanolamine hydrochloride.
  11. The implications of knowledge hiding at work for recovery after work: A diary study
  12. Assessing empirical research on value-based management
  13. Disentangling trade-offs and synergies around ecosystem services with the influence network framework
  14. Acquisitional pragmatics
  15. Embracing scale-dependence to achieve a deeper understanding of biodiversity and its change across communities
  16. Exports and productivity: A survey of the evidence from firm-level data
  17. Leaf trait variation within individuals mediates the relationship between tree species richness and productivity
  18. Current overview of research on priority effects and its relevance to restoration
  19. Decentralized control of assembly processes driven by Gentelligent® Parts
  20. Using latent class analysis to produce a typology of environmental concern in the UK
  21. Conception of an indirectly controlled servo valve for IC engine valve position control
  22. Independence without control
  23. Introduction
  24. Smart cities, smart borders. Sensing networks and security in the urban space
  25. Number theoretical peculiarities in the dimension theory of dynamical systems
  26. Importance of timing
  27. Uncertainty, Pluralism, and the Knowledge-based Theory of the Firm
  28. Mapping of Innovation Relations
  29. Diversity and specialization of host parasitoid interactions in an urban rural interface
  30. Initial evidence for a systematic link between core values and emotional experiences in environmental situations
  31. EEG frequency tagging evidence of intact social interaction recognition in adults with autism
  32. Differences in the earnings distribution of self- and dependent employed German men
  33. Quo Vadis, Umweltinformatik? 6. Workshop
  34. Ecologies of things and texts
  35. Democratization as Human Empowerment
  36. From Feedback to Formative Guidance
  37. Leverage points and levers of inclusive conservation in protected areas
  38. Governance statt Management oder: Management der Governance
  39. A highly endangered species on the edge
  40. Targeted metabolomics of pellicle and saliva in children with different caries activity