research-article

Cost-Sensitive Boosting Pruning Trees for Depression Detection on Twitter

Authors:

Xiangrong Zhang,

Huiyu ZhouAuthors Info & Claims

IEEE Transactions on Affective Computing, Volume 14, Issue 3

Pages 1898 - 1911

https://doi.org/10.1109/TAFFC.2022.3145634

Published: 01 July 2023 Publication History

Abstract

Depression is one of the most common mental health disorders, and a large number of depressed people commit suicide each year. Potential depression sufferers usually do not consult psychological doctors because they feel ashamed or are unaware of any depression, which may result in severe delay of diagnosis and treatment. In the meantime, evidence shows that social media data provides valuable clues about physical and mental health conditions. In this paper, we argue that it is feasible to identify depression at an early stage by mining online social behaviours. Our approach, which is innovative to the practice of depression detection, does not rely on the extraction of numerous or complicated features to achieve accurate depression detection. Instead, we propose a novel classifier, namely, Cost-sensitive Boosting Pruning Trees (CBPT), which demonstrates a strong classification ability on two publicly accessible Twitter depression detection datasets. To comprehensively evaluate the classification capability of CBPT, we use additional three datasets from the UCI machine learning repository and CBPT obtains appealing classification results against several state of the arts boosting algorithms. Finally, we comprehensively explore the influence factors for the model prediction, and the results manifest that our proposed framework is promising for identifying Twitter users with depression.

References

[1]

R. Cheng et al., “Genome-wide linkage scan in a large bipolar disorder sample from the national institute of mental health genetics initiative suggests putative loci for bipolar disorder, psychosis, suicide, and panic disorder,” Mol. Psychiatry, vol. 11, no. 3, 2006, Art. no.

[2]

S. McManus, H. Meltzer, T. Brugha, P. Bebbington, and R. Jenkins, Adult Psychiatric Morbidity in England: Results of a Household Survey. Health and Social Care Informat. Centre, 2009.

[3]

L. Andrade et al., “The epidemiology of major depressive episodes: Results from the international consortium of psychiatric epidemiology (icpe) surveys,” Int. J. Methods Psychiatr. Res., vol. 12, no. 1, pp. 3–21, 2003.

[4]

L. S. Radloff, “The CES-D scale: A self-report depression scale for research in the general population,” Appl. Psychol. Meas., vol. 1, no. 3, pp. 385–401, 1977.

[5]

Y. Yang, C. Fairbairn, and J. F. Cohn, “Detecting depression severity from vocal prosody,” IEEE Trans. Affect. Comput., vol. 4, no. 2, pp. 142–150, Second quarter 2013.

Digital Library

[6]

S. Alghowinem et al., “Multimodal depression detection: Fusion analysis of paralinguistic, head pose and eye gaze behaviors,” IEEE Trans. Affect. Comput., vol. 9, no. 4, pp. 478–490, Fourth quarter 2016.

Digital Library

[7]

G. Shen et al., “Depression detection via harvesting social media: A multimodal dictionary learning solution,” in Proc. 26th Int. Joint Conf. Artif. Intell., 2017, pp. 3838–3844.

[8]

R. González-Ibánez, S. Muresan, and N. Wacholder, “Identifying sarcasm in twitter: A closer look,” in Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol., 2011, pp. 581–586.

[9]

M. De Choudhury, M. Gamon, S. Counts, and E. Horvitz, “Predicting depression via social media,” in Proc. 7th Int. AAAI Conf. Weblogs Social Media, 2013, pp. 1–10.

[10]

Y. Neuman, Y. Cohen, D. Assaf, and G. Kedma, “Proactive screening for depression through metaphorical and automatic text analysis,” Artif. Intell. Med., vol. 56, no. 1, pp. 19–25, 2012.

Digital Library

[11]

M. Zaydman, “Tweeting about mental health,” Ph.D. dissertation, Pardee RAND Graduate School, Santa Monica, CA, USA, 2017.

[12]

M. Akbari, X. Hu, L. Nie, and T.-S. Chua, “From tweets to wellness: Wellness event detection from twitter streams,” in Proc. 13th AAAI Conf. Artif. Intell., 2016, pp. 87–93.

[13]

G. Coppersmith, M. Dredze, and C. Harman, “Quantifying mental health signals in twitter,” in Proc. Workshop Comput. Linguistics Clin. Psychol., From Linguistic Signal Clin. Reality, 2014, pp. 51–60.

[14]

S. Salawu, Y. He, and J. Lumsden, “Approaches to automated detection of cyberbullying: A survey,” IEEE Trans. Affect. Comput., vol. 11, no. 1, pp. 3–24, First quarter 2017.

[15]

T. Nguyen, D. Phung, B. Dao, S. Venkatesh, and M. Berk, “Affective and content analysis of online depression communities,” IEEE Trans. Affect. Comput., vol. 5, no. 3, pp. 217–226, Third quarter 2014.

[16]

Y. Freund, R. E. Schapire, “Experiments with a new boosting algorithm,” in Proc. 13th Int. Conf. Int. Mach. Learn., 1996, pp. 148–156.

[17]

Y. Lee, M.-J. Yang, T.-J. Lai, N.-M. Chiu, and T. Chau, “Development of the taiwanese depression questionnaire,” Chang Gung Med. J., vol. 23, pp. 688–694, 2000.

[18]

M. Park, D. W. McDonald, and M. Cha, “Perception differences between the depressed and non-depressed users in twitter,” in Proc. 7th Int. AAAI Conf. Weblogs Social Media, 2013, pp. 476–485.

[19]

M. Park, C. Cha, and M. Cha, “Depressive moods of users portrayed in twitter,” in Proc. ACM SIGKDD Workshop Healthcare Inform., 2012, pp. 1–8.

[20]

A. Hussain, J. Heidemann, and C. Papadopoulos, “A framework for classifying denial of service attacks,” in Proc. Conf. Appl. Technol. Archit. Protoc. Comput. Commun., 2003, pp. 99–1103.

[21]

M. Nadeem, “Identifying depression on twitter,” 2016,.

[22]

H.-H. Shuai et al., “A comprehensive study on social network mental disorders detection via online social media mining,” IEEE Trans. Knowl. Data Eng., vol. 30, no. 7, pp. 1212–1225, Jul. 2018.

[23]

T. Shen et al., “Cross-domain depression detection via harvesting social media,” in Proc. 27th Int. Joint Conf. Artif. Intell., 2018, pp. 1611–1617.

[24]

A. Ray, S. Kumar, R. Reddy, P. Mukherjee, and R. Garg, “Multi-level attention network using text, audio and video for depression prediction,” in Proc. 9th Int. Audio/Vis. Emotion Challenge Workshop, 2019, pp. 81–88.

[25]

P. K. Gamaarachchige and D. Inkpen, “Multi-task, multi-channel, multi-input learning for mental illness detection using social media text,” in Proc. 10th Int. Workshop Health Text Mining Informat. Anal, 2019, pp. 54–64.

[26]

G. Coppersmith, M. Dredze, C. Harman, K. Hollingshead, and M. Mitchell, “CLPsych 2015 shared task: Depression and PTSD on twitter,” in Proc. 2nd Workshop Comput. Linguistics Clin. Psychol., From Linguistic Signal Clin. Reality, 2015, pp. 31–39. [Online]. Available: https://www.aclweb.org/anthology/W15–1204

[27]

A. H. Orabi, P. Buddhitha, M. H. Orabi, and D. Inkpen, “Deep learning for depression detection of twitter users,” in Proc. 5th Workshop Comput. Linguistics Clin. Psychol., From Keyboard Clin., 2018, pp. 88–97.

[28]

C. Molnar, Interpretable Mach. Learn.. 2020. [Online]. Available: Lulu.com

[29]

D. Ignatov and A. Ignatov, “Decision stream: Cultivating deep decision trees,” in Proc. IEEE 29th Int. Conf. Tools Artif. Intell., 2017, pp. 905–912.

[30]

G. Leshem, “Improvement of adaboost algorithm by using random forests as weak learner and using this algorithm as statistics machine learning for traffic flow prediction,” Ph.D. thesis, The Dep. statistics, The Hebrew Univ. Jerusalem, Jerusalem, Israel, 2005.

[31]

G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning, vol. 112. New York, USA: Springer, 2013.

[32]

L. Breiman, “Bias, variance, and arcing classifiers,” Statistics Dep., Univ. California, Berkeley, CA, USA, Tech. Rep. 460, 1996.

[33]

N. Boonyanunta and P. Zeephongsekul, “Improving the predictive power of adaboost: A case study in classifying borrowers,” in Proc. Int. Conf. Ind. Eng. Other Appl. Appl. Intell. Syst., 2003, pp. 674–685.

[34]

J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Statist., vol. 29, no. 5, pp. 1189–1232, 2001.

[35]

T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2016, pp. 785–794.

[36]

A. H. Yazdavar, et al., “Semi-supervised approach to monitoring clinical depressive symptoms in social media,” in Proc. IEEE/ACM Int. Conf. Adv. Social Netw. Anal. Mining, 2017, pp. 1191–1198.

[37]

S. Loria et al., “TextBlob: Simplified text processing,” Secondary TextBlob: Simplified Text Process., 2014.

[38]

M. Porter and R. Boulton, “Snowball stemmer,” 2001.

[39]

M. De Choudhury, S. Counts, and E. Horvitz, “Social media as a measurement tool of depression in populations,” in Proc. 5th Annu. ACM Web Sci. Conf., 2013, pp. 47–56.

[40]

S. Bird and E. Loper, “NLTK: The natural language toolkit,” in Proc. ACL Interactive Poster Demonstration Sessions, 2004, pp. 214–217.

[41]

P. Resnik, W. Armstrong, L. Claudino, T. Nguyen, V.-A. Nguyen, and J. Boyd-Graber, “Beyond LDA: Exploring supervised topic modeling for depression-related language in twitter,” in Proc. 2nd Workshop Comput. Linguistics Clin. Psychol., From Linguistic Signal Clin. Reality, 2015, pp. 99–107.

[42]

D. M. Blei, A. Y. Ng, and M. I. Jordan, “Latent dirichlet allocation,” J. Mach. Learn. Res., vol. 3, pp. 993–1022, 2003.

[43]

L. Breiman, Classification and Regression Trees. Evanston, IL, USA: Routledge, 2017.

[44]

H. Kokel, P. Odom, S. Yang, and S. Natarajan, “A unified framework for knowledge intensive gradient boosting: Leveraging human experts for noisy sparse domains,” in Proc. AAAI Conf. Artif. Intell., 2020, pp. 4460–4468.

[45]

W.-Y. Loh, “Classification and regression trees,” Wiley Interdiscipl. Rev., Data Mining Knowl. Discov., vol. 1, no. 1, pp. 14–23, 2011.

[46]

F. Pedregosa et al., “Scikit-learn: Machine learning in python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.

Digital Library

[47]

A. Asuncion and D. Newman, “UCI machine learning repository,” 2007.

[48]

T. Hastie, S. Rosset, J. Zhu, and H. Zou, “Multi-class adaboost,” Statist. Interface, vol. 2, no. 3, pp. 349–360, 2009.

[49]

P. Li, “Robust logitboost and adaptive base class (abc) logitboost,” 2012,.

[50]

G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” in Proc. 31st Int. Conf. Adv. Neural Inf. Process. Syst., 2017, pp. 3149–3157.

[51]

X. Song, L. Nie, L. Zhang, M. Akbari, and T.-S. Chua, “Multiple social network learning and its application in volunteerism tendency prediction,” in Proc. 38th Int. ACM SIGIR Conf. Res. Develop. Informat. Retrieval, 2015, pp. 213–222.

[52]

A. Rolet, M. Cuturi, and G. Peyré, “Fast dictionary learning with a smoothed wasserstein loss,” in Proc. 19th Int. Conf. Artif. Intell. Statist., 2016, pp. 630–638.

[53]

P. Resnik, W. Armstrong, L. Claudino, and T. Nguyen, “The university of maryland clpsych 2015 shared task system,” in Proc. 2nd Workshop Comput. Linguistics Clin. Psychol., From Linguistic Signal Clin. Reality, 2015, pp. 54–60.

[54]

D. Preoţiuc-Pietro, M. Sap, H. A. Schwartz, and L. Ungar, “Mental illness detection at the world well-being project for the clpsych 2015 shared task,” in Proc. 2nd Workshop Comput. Linguistics Clin. Psychol., From Linguistic Signal Clin. Reality, 2015, pp. 40–45.

[55]

T. Pedersen, “Screening twitter users for depression and PTSD with lexical decision lists,” in Proc. 2nd Workshop Comput. Linguistics Clin. Psychol., From Linguistic Signal Clin. Reality, 2015, pp. 46–53.

[56]

Z. Jamil, D. Inkpen, P. Buddhitha, and K. White, “Monitoring tweets for depression to detect at-risk users,” in Proc. 4th Workshop Comput. Linguistics Clin. Psychol. —From Linguistic Signal Clin. Reality, 2017, pp. 32–40.

[57]

S. M. Lundberg et al., “From local explanations to global understanding with explainable ai for trees,” Nature Mach. Intell., vol. 2, no. 1, pp. 56–67, 2020.

[58]

L. S. Shapley, Notes on the N-person Game–II: The Value of an N-person Game. Santa Monica, CA, USA: Rand Corporation, 1951.

Cited By

Gan LGuo YYang T(2024)Machine Learning for Depression Detection on Web and Social MediaInternational Journal on Semantic Web & Information Systems10.4018/IJSWIS.34212620:1(1-28)Online publication date: 15-May-2024
https://dl.acm.org/doi/10.4018/IJSWIS.342126
Montejo-Ráez AMolina-González MJiménez-Zafra SGarcía-Cumbreras MGarcía-López L(2024)A survey on detecting mental disorders with natural language processingComputer Science Review10.1016/j.cosrev.2024.10065453:COnline publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1016/j.cosrev.2024.100654
Liu Y(2024)Depression detection via a Chinese social media platform: a novel causal relation-aware deep learning approachThe Journal of Supercomputing10.1007/s11227-023-05830-y80:8(10327-10356)Online publication date: 1-May-2024
https://dl.acm.org/doi/10.1007/s11227-023-05830-y

Recommendations

Cost-Sensitive Boosting

A novel framework is proposed for the design of cost-sensitive boosting algorithms. The framework is based on the identification of two necessary conditions for optimal cost-sensitive learning that 1) expected losses must be minimized by optimal cost-...
Expression of Depression Among Arab Twitter Users Using Arabic Corpus Analysis
Abstract
Expressing emotions on social media is becoming popular by the day. Several studies have documented the relation between how people express their emotions to their mental state e.g., depression. Most of these studies were conducted in English, ...
Cost-Sensitive Boosting: Fitting an Additive Asymmetric Logistic Regression Model
ACML '09: Proceedings of the 1st Asian Conference on Machine Learning: Advances in Machine Learning

Conventional machine learning algorithms like boosting tend to equally treat misclassification errors that are not adequate to process certain cost-sensitive classification problems such as object detection. Although many cost-sensitive extensions of ...

Comments

Information & Contributors

Information

Published In

cover image IEEE Transactions on Affective Computing

IEEE Transactions on Affective Computing Volume 14, Issue 3

July-Sept. 2023

853 pages

ISSN:1949-3045

Issue’s Table of Contents

1949-3045 © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Publisher

IEEE Computer Society Press

Washington, DC, United States

Publication History

Published: 01 July 2023

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 10 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Gan LGuo YYang T(2024)Machine Learning for Depression Detection on Web and Social MediaInternational Journal on Semantic Web & Information Systems10.4018/IJSWIS.34212620:1(1-28)Online publication date: 15-May-2024
https://dl.acm.org/doi/10.4018/IJSWIS.342126
Montejo-Ráez AMolina-González MJiménez-Zafra SGarcía-Cumbreras MGarcía-López L(2024)A survey on detecting mental disorders with natural language processingComputer Science Review10.1016/j.cosrev.2024.10065453:COnline publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1016/j.cosrev.2024.100654
Liu Y(2024)Depression detection via a Chinese social media platform: a novel causal relation-aware deep learning approachThe Journal of Supercomputing10.1007/s11227-023-05830-y80:8(10327-10356)Online publication date: 1-May-2024
https://dl.acm.org/doi/10.1007/s11227-023-05830-y

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents