Leveraging Routine Behavior and Contextually-Filtered Features for Depression Detection among College Students
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
The rate of depression in college students is rising, which is known to increase suicide risk, lower academic performance and double the likelihood of dropping out of school. Existing work on finding relationships between passively sensed behavior and depression, as well as detecting depression, mainly derives relevant unimodal features from a single sensor. However, co-occurrence of values in multiple sensors may provide better features, because such features can describe behavior in context. We present a new method to extract contextually filtered features from passively collected, time-series mobile data via association rule mining. After calculating traditional unimodal features from the data, we extract rules that relate unimodal features to each other using association rule mining. We extract rules from each class separately (e.g., depression vs. non-depression). We introduce a new metric to select a subset of rules that distinguish between the two classes. From these rules, which capture the relationship between multiple unimodal features, we automatically extract contextually filtered features. These features are then fed into a traditional machine learning pipeline to detect the class of interest (in our case, depression), defined by whether a student has a high BDI-II score at the end of the semester. The behavior rules generated by our methods are highly interpretable representations of differences between classes. Our best model uses contextually-filtered features to significantly outperform a standard model that uses only unimodal features, by an average of 9.7% across a variety of metrics. We further verified the generalizability of our approach on a second dataset, and achieved very similar results.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Beck, A. T., Steer, R. A., & Brown, G. (2011) · PsycTESTS Dataset · doi:10.1037/t00742-000 · Cited by 7,535 · cited 4×
“Students with a post-semester BDI-II score greater than 13 were in the depression group, in accord with the interpretation of the BDI-II [12].”
BackgroundMethodInfluentialVos, T., Allen, C., Arora, M., Barber, R. M., Bhutta, Z. A., Brown, A., Carter, A., Casey, D. C., Charlson, F. J., Chen, A. Z., et al. (2016) · The Lancet · doi:10.1016/s0140-6736(16)31678-6 · Cited by 7,253
The Epidemiology of Depression Across Cultures
Kessler, R. C., & Bromet, E. J. (2013) · Annual Review of Public Health · doi:10.1146/annurev-publhealth-031912-114409 · Cited by 2,657
A survey of mobile phone sensing
Lane, N., Miluzzo, E., Lu, H., Peebles, D., Choudhury, T., & Campbell, A. (2010) · IEEE Communications Magazine · doi:10.1109/mcom.2010.5560598 · Cited by 2,292
Demirci, K., Akgönül, M., & Akpinar, A. (2015) · Journal of Behavioral Addictions · doi:10.1556/2006.4.2015.010 · Cited by 1,529 · cited 3×
“The former might impact features such as time in bed, while the latter might impact a metric such as phone use, which could rise with distraction and depression [24].”
BackgroundDetecting anxiety and depression in general medical settings.
Goldberg, D., Bridges, K., Duncan-Jones, P., & Grayson, D. (1988) · BMJ · doi:10.1136/bmj.297.6653.897 · Cited by 1,210
Help-Seeking and Access to Mental Health Care in a University Student Population
Eisenberg, D., Golberstein, E., & Gollust, S. E. (2007) · Medical Care · doi:10.1097/mlr.0b013e31803bb4c1 · Cited by 1,131 · cited 1×
“Yet many of them do not even realize they are depressed until they begin experiencing severe functional deterioration [22, 46], and even those that do may not seek health treatment [29, 40].”
BackgroundWang, R., Chen, F., Chen, Z., Li, T., Harari, G., Tignor, S., Zhou, X., Ben-Zeev, D., & Campbell, A. T. (2014) · Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2632048.2632054 · Cited by 1,116
Tsuno, N., Besset, A., & Ritchie, K. (2005) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.v66n1008 · Cited by 1,084
Visualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845 · cited 1×
“Although current deep-learning models are relatively less interpretable, more and more works try to understand the principle of neural network [48].”
BackgroundCPAR: Classification based on Predictive Association Rules
Yin, X., & Han, J. (2003) · Proceedings of the 2003 SIAM International Conference on Data Mining · doi:10.1137/1.9781611972733.40 · Cited by 833
Saeb, S., Zhang, M., Karr, C. J., Schueller, S. M., Corden, M. E., Kording, K. P., & Mohr, D. C. (2015) · Journal of Medical Internet Research · doi:10.2196/jmir.4273 · Cited by 782 · cited 10×
“Over the past few years, diferent studies have identifed signifcant correlations between mobile sensing data and depression [27, 70, 86].”
BackgroundMethodResultInfluentialStorch, E. A., Roberti, J. W., & Roth, D. A. (2004) · Depression and Anxiety · doi:10.1002/da.20002 · Cited by 694
Nock, M. K., & Kessler, R. C. (2006) · Journal of Abnormal Psychology · doi:10.1037/0021-843x.115.3.616 · Cited by 680 · cited 1×
“Moreover, depression is one of the most common symptoms among people with suicidal propensity [52, 64].”
BackgroundHarnessing context sensing to develop a mobile intervention for depression
Burns, M. N., Begale, M., Duffecy, J., Gergle, D., Karr, C. J., Giangrande, E., & Mohr, D. C. (2011) · Journal of Medical Internet Research · doi:10.2196/jmir.1838 · Cited by 646 · cited 1×
“A rich body of literature has suggested the importance of contextual information ( e.g. , [1, 25]) for depression detection [18, 83].”
BackgroundKisch, J., Leino, E. V., & Silverman, M. M. (2005) · Suicide and Life-Threatening Behavior · doi:10.1521/suli.35.1.3.59263 · Cited by 489 · cited 1×
“Moreover, depression is one of the most common symptoms among people with suicidal propensity [52, 64].”
BackgroundCanzian, L., & Musolesi, M. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2805845 · Cited by 477
Ben-Zeev, D., Scherer, E. A., Wang, R., Xie, H., & Campbell, A. T. (2015) · Psychiatric Rehabilitation Journal · doi:10.1037/prj0000130 · Cited by 429 · cited 1×
“Further analysis of this dataset also found signifcant relationships between changes in depression scores and features such as sleep duration, speech duration, and mobility [13].”
BackgroundAWARE: Mobile Context Instrumentation Framework
Ferreira, D., Kostakos, V., & Dey, A. K. (2015) · Frontiers in ICT · doi:10.3389/fict.2015.00006 · Cited by 409 · cited 1×
“We installed the AWARE framework [32] to collect sensor data unobtru-sively from students’ smartphones.”
MethodSelf-citationCzyz, E. K., Horwitz, A. G., Eisenberg, D., Kramer, A., & King, C. A. (2013) · Journal of American College Health · doi:10.1080/07448481.2013.820731 · Cited by 388 · cited 1×
“Yet many of them do not even realize they are depressed until they begin experiencing severe functional deterioration [22, 46], and even those that do may not seek health treatment [29, 40].”
BackgroundTracking Depression Dynamics in College Students Using Mobile Phone and Wearable Sensing
Wang, R., Wang, W., daSilva, A., Huckins, J. F., Kelley, W. M., Heatherton, T. F., & Campbell, A. T. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3191775 · Cited by 340 · cited 10×
“…a relationship between depression and both mobility and sleep, that not only echoes previous literature regarding the efect of depression on sleep [7, 87], but also is supported by the fndings of other studies similar to ours which show that depression and diminished locomotion co-occur [19, 70].”
BackgroundMethodResultInfluentialMobile Sensing and Support for People With Depression: A Pilot Trial in the Wild
Wahle, F., Kowatsch, T., Fleisch, E., Rufer, M., & Weidt, S. (2016) · JMIR mHealth and uHealth · doi:10.2196/mhealth.5960 · Cited by 333 · cited 8×
“However, these baselines provide strong evidence that our model is either better than previous work [19, 30, 84], or comparable to the state-of-the-art [70, 87].”
BackgroundMethodResultInfluentialThe relationship between mobile phone location sensor data and depressive symptom severity
Saeb, S., Lattie, E. G., Schueller, S. M., Kording, K. P., & Mohr, D. C. (2016) · PeerJ · doi:10.7717/peerj.2537 · Cited by 313
Chow, P. I., Fua, K., Huang, Y., Bonelli, W., Xiong, H., Barnes, L. E., & Teachman, B. A. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.6820 · Cited by 172
DeepMood: Forecasting Depressed Mood Based on Self-Reported Histories via Recurrent Neural Networks
Suhara, Y., Xu, Y., & Pentland, A. '. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052676 · Cited by 163
Behavior vs. introspection: refining prediction of clinical depression via smartphone sensing data
Farhan, A. A., Yue, C., Morillo, R., Ware, S., Lu, J., Bi, J., Kamath, J., Russell, A., Bamis, A., & Wang, B. (2016) · 2016 IEEE Wireless Health (WH) · doi:10.1109/wh.2016.7764553 · Cited by 115
Associating internet usage with depressive behavior among college students
Katikalapudi, R., Chellappan, S., Montgomery, F., Wunsch, D., & Lutzen, K. (2012) · IEEE Technology and Society Magazine · doi:10.1109/mts.2012.2225462 · Cited by 81 · cited 1×
“Katikalapudi et al. [49] ran a month-long study with 216 college students and found a direct relationship between depressive symptoms and Internet use.”
BackgroundDepression Estimation Using Audiovisual Features and Fisher Vector Encoding
Jain, V., Crowley, J. L., Dey, A. K., & Lux, A. (2014) · Proceedings of the 4th International Workshop on Audio/Visual Emotion Challenge · doi:10.1145/2661806.2661817 · Cited by 78
Self-citationWahle, F., Bollhalder, L., Kowatsch, T., & Fleisch, E. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.7381 · Cited by 48 · cited 2×
“…smartwatches), that consistently and passively collect behavioral sensor data, can help us to understand the relationship between people’s daily behavior and depression [8, 19, 55], complement traditional screening methods and provide the potential for introducing real-time interventions [83, 84].”
BackgroundRuleSelector: Selecting Conditional Action Rules from User Behavior Patterns
Srinivasan, V., Koehler, C., & Jin, H. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3191767 · Cited by 23
Research works printed but not linked: 63
- 10.5555/647985.743843 · doi:10.5555/647985.743843
- Substance Abuse , Mental Health Services Administration, et al . 2016 . 2015 National Survey on Drug Use and Health . (2016). Substance Abuse, Mental Health Services Administration, et al. 2016. 2015 National Survey on Drug Use and Health. (2016).
- ACHA-NCHA II 2018. Undergraduate Student Reference Group - Data Report. https://www.acha.org/documents/ncha/NCHA-II_Spring_2018_Undergraduate_Reference_Group_Data_Report.pdf. {Online ; accessed 19- July - 2008 }. ACHA-NCHA II 2018. Undergraduate Student Reference Group - Data Report. https://www.acha.org/documents/ncha/NCHA-II_Spring_2018_Undergraduate_Reference_Group_Data_Report.pdf. {Online; accessed 19-July-2008}.
- Rakesh Agrawal and Ramakrishnan Srikant . 1994 . Fast algorithms for mining association rules . In Proceedings of 20th International Conference on Very Large Data Bases, VLDB , Vol. 1215 . 487--499. Rakesh Agrawal and Ramakrishnan Srikant. 1994. Fast algorithms for mining association rules. In Proceedings of 20th International Conference on Very Large Data Bases, VLDB, Vol. 1215. 487--499.
- 10.5555/645480.655281 · doi:10.5555/645480.655281
- 10.5555/3012377.3012388 · doi:10.5555/3012377.3012388
- American Psychiatric Association et al. 2013. Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Pub. American Psychiatric Association et al. 2013. Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Pub. · DOI · Paper page
- 10.1109/JSTSP.2016.2565381 · DOI · Paper page
- 10.1145/2858036.2858557 · DOI · Paper page
- 10.1145/3025453.3025571 · DOI
- Aaron T. Beck . 1979. Cognitive therapy of depression . Guilford press . Aaron T. Beck. 1979. Cognitive therapy of depression. Guilford press.
- 10.1007/978-3-642-04180-8_25 · DOI · Paper page
- 10.1145/1520340.1520621 · DOI
- 10.1145/1719970.1720011 · DOI · Paper page
- George W. Brown Bernice Andrews Tirril Harris Zsuzsanna Adler and L. Bridge. 1986. Social support self-esteem and depression. Psychological medicine 16 4 (1986) 813--831. George W. Brown Bernice Andrews Tirril Harris Zsuzsanna Adler and L. Bridge. 1986. Social support self-esteem and depression. Psychological medicine 16 4 (1986) 813--831. · DOI · Paper page
- 10.1145/1871437.1871702 · DOI · Paper page
- 10.1016/j.jad.2018.02.064 · DOI
- 10.1007/s007790170019 · DOI · Paper page
- Afsaneh Doryab . 2018. Identifying symptoms using technology . In Technology and Adolescent Mental Health . Springer , 135--153. Afsaneh Doryab. 2018. Identifying symptoms using technology. In Technology and Adolescent Mental Health. Springer, 135--153.
- Afsaneh Doryab , Jun-Ki Min , Jason Wiese , John Zimmerman , and Jason I. Hong . 2014. Detection of behavior change in people with depression . In AAAI Workshop: Modern Artificial Intelligence for Health Analytics. Afsaneh Doryab, Jun-Ki Min, Jason Wiese, John Zimmerman, and Jason I. Hong. 2014. Detection of behavior change in people with depression. In AAAI Workshop: Modern Artificial Intelligence for Health Analytics.
- 10.1037/1040-3590.10.2.83 · DOI · Paper page
- 10.1109/ISWC.2012.20 · DOI
- 10.5555/2627435.2750353 · doi:10.5555/2627435.2750353
- 10.1007/978-3-319-12571-8_10 · DOI
- 10.1006/jcss.1997.1504 · DOI · Paper page
- 10.1145/2493432.2493507 · DOI · Paper page
- 10.1016/j.jpsychores.2009.05.003 · DOI · Paper page
- 10.1145/1132960.1132963 · DOI · Paper page
- Darcy Gruttadaro and Dana Crudo . 2012. College students speak: A survey report on mental health. National Alliance on Mental Illness ( 2012 ). Darcy Gruttadaro and Dana Crudo. 2012. College students speak: A survey report on mental health. National Alliance on Mental Illness (2012).
- Alketa Hysenbegasi , Steven L Hass , and Clayton R Rowland . 2005 . The impact of depression on the academic productivity of university students . Journal of Mental Health Policy and Economics 8 , 3 (2005), 145 . Alketa Hysenbegasi, Steven L Hass, and Clayton R Rowland. 2005. The impact of depression on the academic productivity of university students. Journal of Mental Health Policy and Economics 8, 3 (2005), 145.
- 10.1007/978-3-319-47665-0_16 · DOI
- 10.5555/645805.670137 · doi:10.5555/645805.670137
- Richard Kadison and Theresa Foy DiGeronimo . 2004. College of the overwhelmed: The campus mental health crisis and what to do about it. San Francisco ( 2004 ). Richard Kadison and Theresa Foy DiGeronimo. 2004. College of the overwhelmed: The campus mental health crisis and what to do about it. San Francisco (2004).
- 10.1145/1414004.1414051 · doi:10.1145/1414004.1414051
- 10.1007/11875581_110 · DOI
- Sotiris Kotsiantis and Dimitris Kanellopoulos . 2006 . Association rules mining: A recent overview . GESTS International Transactions on Computer Science and Engineering 32 , 1 (2006), 71 -- 82 . Sotiris Kotsiantis and Dimitris Kanellopoulos. 2006. Association rules mining: A recent overview. GESTS International Transactions on Computer Science and Engineering 32, 1 (2006), 71--82.
- 10.1103/PhysRevE.69.066138 · DOI · Paper page
- Bing Liu , Wynne Hsu , and Yiming Ma . 1998 . Integrating classification and association rule mining . In Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining. Bing Liu, Wynne Hsu, and Yiming Ma. 1998. Integrating classification and association rule mining. In Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining.
- 10.1109/TKDE.2013.27 · DOI
- 10.3758/BF03200792 · DOI · Paper page
- 10.1016/j.csda.2008.03.013 · DOI
- 10.1145/3132847.3133014 · DOI
- 10.1145/2307636.2307640 · DOI · Paper page
- 10.1145/2668332.2668348 · DOI
- 10.1109/69.634757 · DOI · Paper page
- 10.1145/3178876.3186052 · DOI
- 10.1023/A:1022643204877 · doi:10.1023/a:1022643204877 · Paper page
- Periyasamy Rajendran and Muthusamy Madheswaran . 2010. Hybrid medical image classification using association rule mining with decision tree algorithm. arXiv preprint arXiv:1001.3503 ( 2010 ). Periyasamy Rajendran and Muthusamy Madheswaran. 2010. Hybrid medical image classification using association rule mining with decision tree algorithm. arXiv preprint arXiv:1001.3503 (2010). · arXiv
- Iqbal H. Sarker and Flora D . Salim . 2018 . Mining user behavioral rules from smartphone data through association analysis. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer , 450--461. Iqbal H. Sarker and Flora D. Salim. 2018. Mining user behavioral rules from smartphone data through association analysis. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 450--461.
- 10.1145/2632048.2632052 · DOI · Paper page
- Robert A. Steer , Gregory. K Brown , Aaron T. Beck , and William C . Sanderson . 2001 . Mean Beck Depression Inventory-II scores by severity of major depressive episode. Psychological Reports 88, 3 suppl (2001), 1075--1076. Robert A. Steer, Gregory. K Brown, Aaron T. Beck, and William C. Sanderson. 2001. Mean Beck Depression Inventory-II scores by severity of major depressive episode. Psychological Reports 88, 3 suppl (2001), 1075--1076.
- Michael E. Thase . 1998. Depression , sleep, and antidepressants. The Journal of Clinical Psychiatry ( 1998 ). Michael E. Thase. 1998. Depression, sleep, and antidepressants. The Journal of Clinical Psychiatry (1998).
- 10.1093/biomet/asm036 · DOI
- 10.1192/S0007125000298474 · DOI · Paper page
- 10.1016/j.asoc.2017.09.013 · doi:10.1016/j.asoc.2017.09.013
- 10.1109/ICDM.2007.86 · DOI · Paper page
- Jin-Mao Wei , Wei-Guo Yi , and Ming-Yang Wang . 2005 . Novel measurement for mining effective association rules . In 2005 International Conference on Machine Learning and Cybernetics , Vol. 3 . IEEE, 1660--1664. Jin-Mao Wei, Wei-Guo Yi, and Ming-Yang Wang. 2005. Novel measurement for mining effective association rules. In 2005 International Conference on Machine Learning and Cybernetics, Vol. 3. IEEE, 1660--1664.
- Wenmin Li , Jiawei Han , and Jian Pei . 2001 . CMAR: accurate and efficient classification based on multiple class-association rules . In Proceedings 2001 IEEE International Conference on Data Mining. 369--376 . Wenmin Li, Jiawei Han, and Jian Pei. 2001. CMAR: accurate and efficient classification based on multiple class-association rules. In Proceedings 2001 IEEE International Conference on Data Mining. 369--376.
- 10.1177/1073191112460273 · DOI · Paper page
- 10.1002/jclp.22188 · DOI · Paper page
- 10.1145/1150402.1150452 · DOI
- 10.1145/1081870.1081907 · DOI · Paper page
- 10.1016/j.jeconom.2015.02.006 · DOI · Paper page
Cited by
Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
Xu, X., Yao, B., Dong, Y., Gabriel, S., Yu, H., Hendler, J., Ghassemi, M., Dey, A. K., & Wang, D. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3643540 · Cited by 278
“, one model for one particular task, such as stress detection [43, 71], depression prediction [36, 98, 110, 111], or suicide risk assessment [26, 33]).”
BackgroundSelf-citationDigital Health Tools for the Passive Monitoring of Depression: A Systematic Review of Methods
de Angel, V., Lewis, S., White, K., Oetzmann, C., Leightley, D., Oprea, E., Lavelle, G., Matcham, F., Pace, A., Mohr, D. C., et al. (2021) · doi:10.1101/2021.07.19.21260786 · Cited by 227
“For example, many studies recruited students, who have different socialisation patterns and smartphone usage to older adults 12,50 .”
BackgroundAbd-Alrazaq, A., AlSaad, R., Shuweihdi, F., Ahmed, A., Aziz, S., & Sheikh, J. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00828-5 · Cited by 138
Digital phenotyping for mental health of college students: a clinical review
Melcher, J., Hays, R., & Torous, J. (2020) · Evidence Based Mental Health · doi:10.1136/ebmental-2020-300180 · Cited by 121
Yang, Z., Xu, X., Yao, B., Rogers, E., Zhang, S., Intille, S., Shara, N., Gao, G. G., & Wang, D. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3659625 · Cited by 120
Self-citation
Metadata
- Authors
- Xu, X., Chikersal, P., Doryab, A., Villalba, D. K., Dutcher, J. M., Tumminia, M. J., Althoff, T., Cohen, S., Creswell, K. G., Creswell, J. D., Mankoff, J., & Dey, A. K.
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2019-09-09
- Volume
- 3
- Issue
- 3
- Pages
- 1-33
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W2972890723
- Cited by
- 124
- References
- 31
- FWCI
- 15.72
- Type
- journal article
- Language
- en
- Open access
- bronze
- Funders
- the National Institute on Disability, Independent Living and Rehabilitation Research (90DPGE0003-01)
- National Science Foundation (IIS1816687,IIS7974751)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.