The DOI matches its Crossref record; 60 of the 61 references it cites were found in a registry or an index.
DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection
Open accessAbstract
The increasing use of electronic forms of communication presents new opportunities in the study of mental health, including the ability to investigate the manifestations of psychiatric diseases unobtrusively and in the setting of patients' daily lives. A pilot study to explore the possible connections between bipolar affective disorder and mobile phone usage was conducted. In this study, participants were provided a mobile phone to use as their primary phone. This phone was loaded with a custom keyboard that collected metadata consisting of keypress entry time and accelerometer movement. Individual character data with the exceptions of the backspace key and space bar were not collected due to privacy concerns. We propose an end-to-end deep architecture based on late fusion, named DeepMood, to model the multi-view metadata for the prediction of mood scores. Experimental results show that 90.31% prediction accuracy on the depression score can be achieved based on session-level mobile phone typing dynamics which is typically less than one minute. It demonstrates the feasibility of using mobile phone metadata to infer mood disturbance and severity.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Others focused on detecting depression by tracking medication, sleep patterns and actions [20], location [11] or keypress acceleration [165].”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [165]
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
Diagnostic and Statistical Manual of Mental Disorders
American Psychiatric Association (2013) · doi:10.1176/appi.books.9780890425596 · Cited by 116,369
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“y, DeepMood provides a late fusion framework. It first models each view of the time series data separately using Gated Recurrent Unit (GRU) [12], a simplified version of Long Short-Term Memory (LSTM) [24]. It then fuses the output of the GRU from each view. As the GRU extracts a latent feature representation out of ea…”
MethodXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 1×
“• XGB: The implementation of a tree boosting system from XGBoost6 [10] is used.”
MethodLearning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 11×
“A typical GRU is formulated as: rk = sigmoid(Wr xk + Ur hk−1) zk = sigmoid(Wzxk + Uzhk−1) h̃k = tanh(Wxk + U(rk ⊙ hk−1)) hk = zk ⊙ hk−1 + (1 − zk ) ⊙ h̃k (3) where ⊙ is the element-wise multiplication operator, a reset gate rk allows the GRU to forget the previously computed state hk−1, and an update gate zk balances…”
BackgroundMethodInfluentialKessler, R. C., Berglund, P., Demler, O., Jin, R., Merikangas, K. R., & Walters, E. E. (2005) · Archives of General Psychiatry · doi:10.1001/archpsyc.62.6.593 · Cited by 20,391 · cited 1×
“There are 7 participants with bipolar I disorder that involves periods of severe mood episodes from mania to depression, 5 participants with bipolar II disorder which is a milder form of mood elevation, involving milder episodes of hypomania that alternate with periods of severe depression, and 8 participants with no…”
BackgroundNeural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 1×
“Inspired by the great success of deep RNNs in the applications of other sequence tasks, including speech recognition [20] and natural language processing [4, 34], in this work, we propose a deep architecture to model complex event sequences of mobile phone typing dynamics.”
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 1×
“The GRU has been attracting great attentions since it overcomes the vanishing gradient problem in traditional RNNs and is more efficient than the LSTM in some tasks [14].”
MethodTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“Inspired by the great success of deep RNNs in the applications of other sequence tasks, including speech recognition [20] and natural language processing [4, 34], in this work, we propose a deep architecture to model complex event sequences of mobile phone typing dynamics.”
A Rating Scale for Mania: Reliability, Validity and Sensitivity
Young, R. C., Biggs, J. T., Ziegler, V. E., & Meyer, D. A. (1978) · British Journal of Psychiatry · doi:10.1192/bjp.133.5.429 · Cited by 8,744 · cited 7×
“Based on the Kolmogorov-Smirnov test, for 98.06% in HDRS and 99.52% in YMRS of the distribution pairs, we can reject the null hypothesis that two samples are drawn from the same distribution with significance level α = 0.01.”
MethodInfluential
Flagged first, then by citations
1 of the 61 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- Tijmen Tieleman and Geoffrey Hinton 2012 . Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude . COURSERA: Neural Networks for Machine Learning , Vol. 4 , 2 (2012). Tijmen Tieleman and Geoffrey Hinton 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, Vol. 4, 2 (2012).
Cited by
Sorted by citations
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450
Deep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2904897 · Cited by 1,913
Self-citationMachine learning in mental health: a scoping review of methods and applications
Shatte, A. B. R., Hutchinson, D. M., & Teague, S. J. (2019) · Psychological Medicine · doi:10.1017/s0033291719000151 · Cited by 1,047
Thieme, A., Belgrave, D., & Doherty, G. (2020) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3398069 · Cited by 406
“Here, success of newly developed models is primarily reported through performance measures of the ‘accuracy of the (best) classifier’ or ‘robustness of clustering’ [2, 4, 6, 23, 27, 33, 44, 45, 50, 57, 61, 62, 63, 64, 67, 86, 89, 112, 122, 128, 133, 134, 135, 136, 139, 141, 144, 145, 152, 153, 155, 165, 168, 176, 177,…”
BackgroundMethodInfluentialDeep neural networks in psychiatry
Durstewitz, D., Koppe, G., & Meyer‐Lindenberg, A. (2019) · Molecular Psychiatry · doi:10.1038/s41380-019-0365-9 · Cited by 297
“They have also been used to monitor PD based on motor movements [115, 116], or to detect depressive states based on typing dynamics [90].”
BackgroundMethodProduct-Based Neural Networks for User Response Prediction over Multi-Field Categorical Data
Qu, Y., Fang, B., Zhang, W., Tang, R., Niu, M., Guo, H., Yu, Y. H., & He, X. (2018) · ACM Transactions on Information Systems · doi:10.1145/3233770 · Cited by 232
“evant work, such as the following.Product Unit Neural Network [11] defines the output of each neuron as the product of all its inputs. Multilinear FM [28] studies FM in a multi-task setting. DeepMood [4] presents a neural network view for FM and Multi-view Machine. 2.3 Net-in-Net Architecture Network In Network (NIN)…”
BackgroundInfluentialMV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation
Cui, Q., Wu, S., Liu, Q., Zhong, W., & Wang, L. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2881260 · Cited by 207
“model multi-view features collected by the mobile phone to predict the mood score [31].”
BackgroundDeep learning for small and big data in psychiatry
Koppe, G., Meyer-Lindenberg, A., & Durstewitz, D. (2021) · Neuropsychopharmacology · doi:10.1038/s41386-020-0767-z · Cited by 189
Thieme, A., Hanratty, M., Lyons, M., Palacios, J. E., Marques, R. F., Morrison, C. P., & Doherty, G. J. (2022) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3564752 · Cited by 197
“…anxiety, or stress—rather than neurological or neurodevelopmental disorders—existing works most commonly utilize (mobile phone) sensor data (i.e., [18, 29, 45, 74, 96, 106, 114]) or text, predominantly sourced from social media (i.e., [19, 58, 72, 78]), to better understand; (earlier) detect; and…”
Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
Wang, J., Zhang, J., Bao, W., Zhu, X., Cao, B., & Yu, P. S. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220106 · Cited by 188
“There is a high demand for the on-device machine learning services, including object recognition, language translation, health monitoring, and many others [6, 15, 28, 41].”
BackgroundMethodSelf-citationA survey on big data-driven digital phenotyping of mental health
Liang, Y., Zheng, X., & Zeng, D. D. (2019) · Information Fusion · doi:10.1016/j.inffus.2019.04.001 · Cited by 164
Dzobo, K., Adotey, S. K., Thomford, N. E., & Dzobo, W. (2019) · OMICS A Journal of Integrative Biology · doi:10.1089/omi.2019.0038 · Cited by 157
“Current studies aim to evaluate whether AI can help predict changes in behavior associated with an onset of depression and other mental health issues (Cao et al., 2017; Gifford et al., 2017).”
Privacy in the age of psychological targeting
Matz, S., Appel, R. E., & Kosiński, M. (2019) · Current Opinion in Psychology · doi:10.1016/j.copsyc.2019.08.010 · Cited by 137
Private Model Compression via Knowledge Distillation
Wang, J., Bao, W., Sun, L., Zhu, X., Cao, B., & Yu, P. S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33011190 · Cited by 122
Self-citationZidaru, T., Morrow, E. M., & Stockley, R. (2021) · Health Expectations · doi:10.1111/hex.13299 · Cited by 143
Deep Learning in Mobile and Wireless Networking: A SurveyPreprint
Zhang, C., Patras, P., & Haddadi, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.04311 · Cited by 121
Self-citationDeep Learning towards Mobile Applications
Wang, J., Cao, B., Yu, P. S., Sun, L., Bao, W., & Zhu, X. (2018) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2018.00139 · Cited by 118
“4: The architecture of DeepMood [3]. automatically generated mobile device data that reflect illness activity could facilitate early intervention and have a potential use as objective outcome measures in efficacy trials [38], [39], [40].”
BackgroundMethodInfluentialSelf-citationSystematic Review of Digital Phenotyping and Machine Learning in Psychosis Spectrum Illnesses
Benoit, J. R. A., Onyeaka, H., Keshavan, M. S., & Torous, J. B. (2020) · Harvard Review of Psychiatry · doi:10.1097/hrp.0000000000000268 · Cited by 116
Privacy-Preserving Federated Depression Detection From Multisource Mobile Health Data
Xu, X., Peng, H. M., Bhuiyan, M. Z. A., Hao, Z., Liu, L., Sun, L., & He, L. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3113708 · Cited by 110
“We use federated learning architecture at the session level to model DeepMood [13], a deep learning architecture based on late fusion.”
MethodZhang, X., Li, W., Chen, X., & Lu, S. (2018) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3161414 · Cited by 100
“DeepMood [8] detected bipolar affective disorder utilizing typing dynamics and accelerometer sensor data in the smartphone based on multi-view neural network.”
BackgroundMethodTouchscreen typing pattern analysis for remote detection of the depressive tendency
Mastoras, R.-E., Iakovakis, D., Hadjidimitriou, S., Charisis, V. S., Kassie, S. A., Alsaadi, T. M., Khandoker, A. H., & Hadjileontiadis, L. J. (2019) · Scientific Reports · doi:10.1038/s41598-019-50002-9 · Cited by 99
“32 , involving the fusion of keystroke timing information, accelerometer data and special characters typed, yielded promising results in terms of prediction of depression scores from bipolar patients and healthy controls, yet without providing insights on interpretability.”
BackgroundMethodInfluentialOnline Purchase Prediction via Multi-Scale Modeling of Behavior Dynamics
Huang, C., Wu, X., Zhang, X., Zhang, C., Zhao, J., Yin, D., & Chawla, N. V. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330790 · Cited by 90
“There exists a good amount of research work in modeling various behavioral time-stamped data [1, 11, 14, 20, 30].”
BackgroundSelf-citationAntosik-Wójcińska, A. Z., Dominiak, M., Chojnacka, M., Kaczmarek‐Majer, K., Opara, K. R., Radziszewska, W., Olwert, A., & Święcicki, Ł. (2020) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2020.104131 · Cited by 85
A Review of Emotion Recognition Methods Based on Data Acquired via Smartphone Sensors
Kołakowska, A., Szwoch, W., & Szwoch, M. (2020) · Sensors · doi:10.3390/s20216367 · Cited by 76
A Survey of Privacy Vulnerabilities of Mobile Device Sensors
Delgado-Santos, P., Stragapede, G., Tolosana, R., Guest, R., Deravi, F., & Vera-Rodríguez, R. (2022) · ACM Computing Surveys · doi:10.1145/3510579 · Cited by 79
“2) Touchscreen: Numerous studies have shown how, from the way a user interacts with the screen of his or her mobile device, it is possible to extract their mood [38, 62, 72, 144].”
BackgroundAlfalahi, H., Khandoker, A. H., Chowdhury, N., Iakovakis, D., Dias, S. B., Chaudhuri, К. R., & Hadjileontiadis, L. J. (2022) · Scientific Reports · doi:10.1038/s41598-022-11865-7 · Cited by 75
Chikersal, P., Belgrave, D. C. M., Doherty, G. J., Enrique, Á., Palacios, J. E., Richards, D., & Thieme, A. (2020) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376341 · Cited by 68
“As is common in ML approaches for mental health, user privacy should be carefully addressed to preserve anonymity (cf. phone data [10, 101], sensors [77], social media [68, 85, 105]), and analysis should occur in a context where there is a clear case for the prospective benefits that could arise,…”
BackgroundIs There an App for That?: Ethical Issues in the Digital Mental Health Response to COVID-19
Skorburg, J. A., & Yam, J. (2021) · AJOB Neuroscience · doi:10.1080/21507740.2021.1918284 · Cited by 65
“An application called DeepMood, for example, predicted depression on the basis of key presses and movements on the smartphone keyboard (Cao et al. 2017).”
MethodMulti-Stage Receptivity Model for Mobile Just-In-Time Health Intervention
Choi, W., Park, S., Kim, D., Lim, Y.-K., & Lee, U. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3328910 · Cited by 71
“Leveraging prior Ubicomp literature on context awareness, such as activity recognition [20], location tracking [35], emotion sensing [11], and even circadian rhythms [1, 46], we can automatically detect opportune moments for JIT support.”
BackgroundBlika, A., Palmos, S., Doukas, G. S., Lamprou, V., Pelekis, S., Kontoulis, M., Ntanos, C., & Askounis, D. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3449563 · Cited by 82
“Reference [134] aim to predict depression using the DeepMood [135] architecture, utilizing the user’s hamilton depression rating scale (HDRS) score and the data recordings created by the user while typing on a mobile device.”
Artificial Intelligence for Social Good: A SurveyPreprint
Shi, Z. R., Wang, C., & Fang, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01818 · Cited by 131
“More generally, there have been e orts to predict suicide risk based on medical history using a set of ordinal classi ers [198] and to detect depression from social media posts using multimodal dictionary learning and transfer learning [199, 200] and mobile phone usage [201].”
MethodEmotion detection from touch interactions during text entry on smartphones
Ghosh, S., Hiware, K., Ganguly, N., Mitra, B., & De, P. (2019) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2019.04.005 · Cited by 58
FedMEC: Improving Efficiency of Differentially Private Federated Learning via Mobile Edge Computing
Zhang, J., Zhao, Y., Wang, J., & Chen, B. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01586-4 · Cited by 52
Predicting physician burnout using clinical activity logs: Model performance and lessons learned
Lou, S. S., Liu, H., Warner, B. C., Harford, D. R., Lu, C., & Kannampallil, T. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104015 · Cited by 54
Wearables, smartphones, and artificial intelligence for digital phenotyping and health
Perez-Pozuelo, I., Spathis, D., Clifton, E. A. D., & Mascolo, C. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-820077-3.00003-1 · Cited by 53
“Other task-specific features include web visits [19], phone recharge [7, 18], ambient sound and light [8, 9, 12], keypress speed [11], compass [12], gyroscope [12], and skin physiology measures [13, 14, 16].”
BackgroundOrsolini, L., Fiorani, M., & Volpe, U. (2020) · International Journal of Molecular Sciences · doi:10.3390/ijms21207684 · Cited by 50
“Moreover, smartphone-based keyboard interaction dynamics appear to be modified depending on the mood state of the subject [20,25].”
BackgroundMethodInfluentialNot Just Privacy: Improving Performance of Private Deep Learning in Mobile CloudPreprint
Wang, J., Zhang, J., Bao, W., Zhu, X., Cao, B., & Yu, P. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.03428 · Cited by 52
“There is a high demand for the on-device machine learning services, including object recognition, language translation, health monitoring, and many others [6, 15, 28, 41].”
BackgroundMethodSelf-citationLenze, E. J., Nicol, G. E., Barbour, D. L., Kannampallil, T., Wong, A. W. K., Piccirillo, J., Drysdale, A. T., Sylvester, C. M., Haddad, R., Miller, J. P., et al. (2021) · Journal of Psychiatry and Neuroscience · doi:10.1503/jpn.200042 · Cited by 43
Khalil, S. S., Tawfik, N. S., & Spruit, M. R. (2024) · Applied Intelligence · doi:10.1007/s10489-023-05095-1 · Cited by 42
“With its three variations, the DeepMood [47] model was used as a clas-sifier, with the data fusion stage being the main variation.”
Passive mobile sensing and psychological traits for large scale mood prediction
Spathis, D., Servia-Rodriguez, S., Farrahi, K., Mascolo, C., & Rentfrow, J. (2019) · Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare · doi:10.1145/3329189.3329213 · Cited by 40
Federated Multi-view Learning for Private Medical Data Integration and Analysis
Che, S., Kong, Z., Peng, H. M., Sun, L., Leow, A., Chen, Y., & He, L. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501816 · Cited by 45
Self-citationWu, X., Shi, B., Dong, Y., Huang, C., Faust, L. J., & Chawla, N. V. (2018) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3269206.3271794 · Cited by 39
“Our work is also related with the research work which focus on mining time-stamped data [3, 11, 24, 41, 44, 46].”
BackgroundMethodPersonalized Federated Learning with Clustering: Non-IID Heart Rate Variability Data Application
Yoo, J. H., Son, H. M., Jeong, H., Jang, E.-H., Kim, A. Y., Yu, H. Y., Jeon, H. J., & Chung, T. (2021) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc52510.2021.9620852 · Cited by 41
DatingSec: Detecting Malicious Accounts in Dating Apps Using a Content-Based Attention Network
He, X., Gong, Q., Chen, Y., Zhang, Y., Wang, X., & Fu, X. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3068307 · Cited by 40
“For the dataset with 10K malicious users, we yield that it is a proper magnitude since Cao et al. [50], Gong et al. [22], and He et al. [51] also used similar numbers of user instances to train the corresponding deep learning models.”
MethodEmoKey: An Emotion-aware Smartphone Keyboard for Mental Health Monitoring
Ghosh, S., Sahu, S., Ganguly, N., Mitra, B., & De, P. (2019) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets.2019.8711078 · Cited by 37
“Existing literature indicates that from smartphone usage it is possible to determine different mental health conditions like stress, bipolar disorder [2], [4], [5].”
BackgroundGupta, A., Maurya, M. K., Dhere, K., & Chaurasiya, V. K. (2024) · IEEE Access · doi:10.1109/access.2024.3464240 · Cited by 45
“Each client holds data from multiple subjects such that when client = 1, then the client holds data from all 15 subject, and client = 3, then each client hold data from 5 subjects, and data is partitioned from all 15 clients to n clients where n ∈ [1 , 14].”
BackgroundInfluentialZhang, D., Lim, J., Zhou, L., & Dahl, A. A. (2021) · JMIR Mental Health · doi:10.2196/31633 · Cited by 43
“These data enable researchers to quantify complex temporal dynamics of important physical (eg, body movement), biological (eg, skin temperature and heart rate), behavioral (eg, phone use behavior and keystrokes), psychological (eg, emotion), social (eg, social interactions with others such as phone calls and SMS text…”
BackgroundMethodLipschitz, J. M., Lin, S., Saghafian, S., Pike, C. K., & Burdick, K. E. (2024) · Acta Psychiatrica Scandinavica · doi:10.1111/acps.13765 · Cited by 40
Fusing Location Data for Depression Prediction
Yue, C., Ware, S., Morillo, R., Lü, J., Shang, C., Bi, J., Kamath, J., Russell, A. C., Bamis, A., & Wang, B. (2018) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2018.2872569 · Cited by 32
“Several recent studies use smartphone sensing data to predict depressive mood or depression [2], [6], [7], [14], [15], [17], [25], [29], [32], [34], [40], [41], [44].”
BackgroundFilling Missing Values on Wearable-Sensory Time Series Data
Lin, S., Wu, X., Martinez, G. J., & Chawla, N. V. (2020) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611976236.6 · Cited by 37
Sequence Multi-task Learning to Forecast Mental Wellbeing from Sparse Self-reported Data
Spathis, D., Servia-Rodriguez, S., Farrahi, K., Mascolo, C., & Rentfrow, J. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330730 · Cited by 30
Arora, A., Chakraborty, P., & Bhatia, M. P. S. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-06078-5 · Cited by 32
“Cao et al. [67] proposed a model named DeepMood which analyses mobile phone typing dynamics (keypress entry time and accelerometer movement) for mood detection and scoring depression.”
BackgrounddpMood: Exploiting Local and Periodic Typing Dynamics for Personalized Mood Prediction
Huang, H., Cao, B., Yu, P. S., Wang, C., & Leow, A. (2018) · Proceedings · doi:10.1109/icdm.2018.00031 · Cited by 31
Self-citationHuman-centred artificial intelligence for mobile health sensing: challenges and opportunities
Dang, T., Spathis, D., Ghosh, A., & Mascolo, C. (2023) · Royal Society Open Science · doi:10.1098/rsos.230806 · Cited by 30
Naturalistic smartphone keyboard typing reflects processing speed and executive function
Ross, M. K., Demos, A. P., Zulueta, J., Piscitello, A., Langenecker, S. A., McInnis, M. G., Ajilore, O., Nelson, P. C., Ryan, K. A., & Leow, A. (2021) · Brain and Behavior · doi:10.1002/brb3.2363 · Cited by 30
“To this end, several recent studies have found that passively collected naturalistic smartphone typing dynamics may be associated with mood state and cognition (Cao et al., 2017; Lam et al., 2020; Mastoras et al., 2019; Vesel et al., 2020; Zulueta et al., 2018).”
BackgroundSelf-citationLinardon, J., Chen, K., Gajjar, S., Eadara, A., Wang, S., Flathers, M., Burns, J., & Torous, J. B. (2025) · Psychiatry Research · doi:10.1016/j.psychres.2025.116483 · Cited by 34
Bennett, C. C., Ross, M. K., Baek, E., Kim, D., & Leow, A. (2022) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2022.101598 · Cited by 26
Self-citationEmotion Detection through Smartphone's Accelerometer and Gyroscope Sensors
Piskioulis, O., Tzafilkou, K., & Economides, A. A. (2021) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3450613.3456822 · Cited by 25
“As shown in [23], DeepMood detected bipolar affective disorder on a multi-view neural network-based Smartphone using typing dynamics and accelerometer sensor data.”
BackgroundFederated learning for Healthcare 5.0: a comprehensive survey, taxonomy, challenges, and solutions
Amin, M., Ahmad, S., & Loh, W.-K. (2025) · Soft Computing · doi:10.1007/s00500-025-10508-z · Cited by 29
“DeepMood (Cao et al. 2017), another DL framework, incorporates FL at the session level, considering the disparity in data quantity and distribution among different healthcare facilities.”
Correlative Channel-Aware Fusion for Multi-View Time Series Classification
Bai, Y., Wang, L., Tao, Z., Li, S., & Fu, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16830 · Cited by 24
“Time series data are collected and analyzed in several domains (Xing, Pei, and Keogh 2010; Cao et al. 2017; Jin and Dong 2016).”
MethodKünstliche Intelligenz in der Psychiatrie – ein Überblick
Meyer‐Lindenberg, A. (2018) · Der Nervenarzt · doi:10.1007/s00115-018-0557-6 · Cited by 22
Forbidden knowledge in machine learning reflections on the limits of research and publication
Hagendorff, T. (2020) · AI & Society · doi:10.1007/s00146-020-01045-4 · Cited by 25
GÜLTEKİN, M., & ŞAHİN, M. (2024) · Cyberpsychology Journal of Psychosocial Research on Cyberspace · doi:10.5817/cp2024-1-6 · Cited by 23
Bennett, C. C., Ross, M. K., Baek, E., Kim, D., & Leow, A. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00741-3 · Cited by 19
“To that end, we focus here on predicting changes in depressive symptoms in bipolar disorder based on data in the weeks prior to the change, in order to allow for a direct comparison to previous research results 6 – 8 .”
BackgroundResultSelf-citationFederated Offline Reinforcement Learning
Zhou, D., Zhang, Y., Sonabend-W, A., Wang, Z., Lu, J., & Cai, T. (2024) · Journal of the American Statistical Association · doi:10.1080/01621459.2024.2310287 · Cited by 22
“Although the aggregation of multi-site data can improve the quality of the models, for the protection of individual information (Agu et al. 2013; Cao et al. 2017), different medical institutions are often not allowed to share data (Hao et al. 2019), which hinders the direct aggregation of…”
Inferring Mood Instability via Smartphone Sensing
Zhang, X., Zhuang, F., Li, W., Ying, H., Xiong, H., & Lu, S. (2019) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3343031.3350957 · Cited by 21
Emotion Sensing for Mobile Computing
Shu, J., Chiu, M., & Hui, P. (2019) · IEEE Communications Magazine · doi:10.1109/mcom.001.1800834 · Cited by 20
“Furthermore, researchers have found that users’ interactions with devices such as typing characteristics [9] and touch screen behaviors [10] may reveal their current emotional states as well.”
BackgroundLearning from Multi-View Multi-Way Data via Structural Factorization Machines
Lu, C.-T., He, L., Ding, H., Cao, B., & Yu, P. S. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3186071 · Cited by 18
Self-citationBraund, T. A., O’Dea, B., Bal, D., Maston, K., Larsen, M. E., Werner‐Seidler, A., Tillman, G., & Christensen, H. M. (2023) · JMIR Mental Health · doi:10.2196/44986 · Cited by 18
“For example, Cao et al [14] and Huang et al [15] first applied deep learning models to keystroke metadata to predict depression and mania symptoms in participants with bipolar disorder from the BiAffect study, yielding high predictive accuracies (~90%).”
InfluentialRuensuk, M., Cheon, E., Hong, H., & Oakley, I. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3432223 · Cited by 21
“To address these problems, several prior studies have built on the observation that smartphone use is associated with affective experiences [97, 122] to use these widely deployed platforms to detect emotional states [19, 28, 68].”
BackgroundMethodResultInfluentialLERIA, L. A., Benítez, P., & Fraga, F. J. (2021) · Education and Information Technologies · doi:10.1007/s10639-020-10419-6 · Cited by 16
“…formation of consortia to automate large-scale assessments for everyone, as well as to make them accessible to PwD (Bennett, 2018; Camilli, 2013; Cao et al., 2017; Higgins & Katz, 2013; IMS Global Learning Consortium, 2009a; Johnstone & Thurlow, 2012; PARCC, 2019; Smarter Balanced Assessment…”
BackgroundSmartphone keyboard dynamics predict affect in suicidal ideation
Knol, L., Nagpal, A., Leaning, I. E., Idda, E., Hussain, F., Ning, E., Eisenlohr-Moul, T. A., Beckmann, C. F., Marquand, A. F., & Leow, A. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01048-1 · Cited by 15
Self-citationFrom Symbols to Embeddings: A Tale of Two Representations in Computational Social Science
Chen, H., Yang, C. H., Zhang, X., Liu, Z., Sun, M., & Jin, J. (2021) · Journal of Social Computing · doi:10.23919/jsc.2021.0011 · Cited by 19
Ross, M. K., Tulabandhula, T., Bennett, C. C., Baek, E., Kim, D., Hussain, F., Demos, A. P., Ning, E., Langenecker, S. A., Ajilore, O., et al. (2023) · Sensors · doi:10.3390/s23031585 · Cited by 16
Self-citationPersonalized Imputation on Wearable-Sensory Time Series via Knowledge Transfer
Wu, X., Mattingly, S. M., Mirjafari, S., Huang, C., & Chawla, N. V. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3411879 · Cited by 14
“The discovered rich regularities from users’ wearable-sensory time series provide rich regularity data that can benefit versatile applications, such as human activity identification [9], emotion detection [3], and demographics inference [36].”
BackgroundRepresentation Learning on Variable Length and Incomplete Wearable-Sensory Time Series
Wu, X., Huang, C., Robles-Granda, P., & Chawla, N. V. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3531228 · Cited by 17
Functional connectivity signatures of political ideology
Yang, S. E., Wilson, J. D., Lu, Z., & Cranmer, S. (2022) · PNAS Nexus · doi:10.1093/pnasnexus/pgac066 · Cited by 13
“CNNs have been increasingly successful not only in image classification and object recognition (43, 44) but also in neuroscience to classify mental or physical disorder such as schizophrenia (45–48), autism (49, 50), depression (51), stages of Alzheimer’s disease (52), and infants born preterm (34).”
BackgroundIn Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study
Carlier, C., Niemeijer, K., Mestdagh, M., Bauwens, M., Vanbrabant, P., Geurts, L., van Waterschoot, T., & Kuppens, P. (2021) · JMIR Mental Health · doi:10.2196/31724 · Cited by 20
Wellness Detection Using Clustered Federated Learning
Gupta, A., Maurya, C., Dhere, K., & Chaurasiya, V. K. (2022) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict56698.2022.9997827 · Cited by 12
Real-Time Monitoring: A Key Element in Personalized Health and Precision Health
Zulueta, J., Leow, A., & Ajilore, O. (2020) · FOCUS The Journal of Lifelong Learning in Psychiatry · doi:10.1176/appi.focus.20190042 · Cited by 11
Self-citationLearning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data
Liang, P. P., Liu, T., Cai, A., Muszyński, M., Ishii, R., Allen, N., Auerbach, R. P., Brent, D. A., Salakhutdinov, R., & Morency, L. (2021) · doi:10.18653/v1/2021.acl-long.322 · Cited by 13
Liu, Q., Ning, E., Ross, M. K., Cladek, A. T., Kabir, S., Barve, A., Kennelly, E., Hussain, F., Duffecy, J. L., Langenecker, S. A., et al. (2024) · Journal of Medical Internet Research · doi:10.2196/51269 · Cited by 10
Self-citationEnergy-efficient Collaborative Sensing: Learning the Latent Correlations of Heterogeneous Sensors
Liang, Y., Wang, X., Yu, Z., Guo, B., Zheng, X., & Samtani, S. (2021) · ACM Transactions on Sensor Networks · doi:10.1145/3448416 · Cited by 10
“The accumulated data of sensors built-in smartphone were collected to predict whether the user is suffering from mental problems such as DeepMood [7, 54] and CrossCheck [61].”
BackgroundHussain, F., Stange, J. P., Langenecker, S. A., McInnis, M. G., Zulueta, J., Piscitello, A., Cao, B., Huang, H., Yu, P. S., Nelson, P. C., et al. (2019) · Studies in neuroscience, psychology and behavioral economics · doi:10.1007/978-3-030-31620-4_10 · Cited by 11
Self-citationNeural Learning of Online Consumer Credit RiskPreprint
Di, W. A. N. G., Wu, Q., & Zhang, W. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3398981 · Cited by 10
Bocu, R., Bocu, D., & Iavich, M. (2022) · Sensors · doi:10.3390/s23010294 · Cited by 11
“Thus, the authors of [158] researched the development of psychiatric diseases using an unobtrusive setup deployed in the patients’ personal environment.”
BackgroundEffectiveness of Mental Health Care by Using Machine Learning on Manufacturing Worker
Lim, J., Lee, S., Noh, J., Lee, W., Su, P., & Yoon, Y. (2023) · International Journal of Precision Engineering and Manufacturing-Smart Technology · doi:10.57062/ijpem-st.2023.0066 · Cited by 9
Making the MOST out of smartphone opportunities for mental health
D’Alfonso, S., Carpenter, N., & Álvarez‐Jiménez, M. (2018) · Australian Conference on Computer-Human Interaction (OzCHI) · doi:10.1145/3292147.3292230 · Cited by 9
Keystroke Dynamics Patterns While Writing Positive and Negative Opinions
Kołakowska, A., & Landowska, A. (2021) · Sensors · doi:10.3390/s21175963 · Cited by 10
“Biometric methods based on keystroke dynamics may be applied in several areas, such as user authentication [3–6], emotion recognition [1,7–12], monitoring mood disorders [13,14] and so forth.”
MethodArtificial Intelligence and Machine Learning in Healthcare Sector
Chavda, V. P., Patel, K., Patel, S. H., & Apostolopoulos, V. (2023) · Wiley eBooks · doi:10.1002/9781119865728.ch13 · Cited by 11
Revolutionizing Mental Healthcare Through Artificial Intelligence
Beg, M. J., & Verma, M. K. (2025) · Advances in medical technologies and clinical practice book series · doi:10.4018/979-8-3693-3112-5.ch002 · Cited by 8
Survey of mood detection through various input modes
Lietz, R., Harraghy, M., Calderon, D., Brady, J., Becker, E., & Makedon, F. S. (2019) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3316782.3321543 · Cited by 8
“Yet another approach to linking phone usage to mood focuses on select features like typing dynamics [5].”
BackgroundRepresentation Learning with Depth and Breadth for Recommendation Using Multi-view Data
Han, X., Shi, C., Zheng, L., Yu, P. S., Li, J., & Lu, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-96890-2_15 · Cited by 8
“In our experiments, we use a simple expression shown in [1] that is equivalent to Multi-view Machine as discussed above.”
MethodSelf-citationData-Fusion-Based Quality Enhancement for HR Measurements Collected by Wearable Sensors
Xia, S., Wung, S., Chen, C., Coompson, J. L. K., Roveda, J. M., & Liu, J. (2024) · Sensors · doi:10.3390/s24102970 · Cited by 7
“Continuous HR monitoring enables the understanding and modeling of the temporal patterns embedded in individuals’ HR data, such as daily activities [17], varying emotions [18], and health status fluctuations.”
BackgroundAssociations between keystroke and stylus metadata and depressive symptoms in adolescents
Jang, M., Cho, Y., Kim, D. H., Park, S., Park, S., Hur, J., Kim, M., Cho, K., Lee, C.-G., & Kwon, J. S. (2024) · Psychological Medicine · doi:10.1017/s0033291724001260 · Cited by 6
Prospects for improved prevention and treatment of neuropsychiatric disorders: Neuroscience Applied
Meyer‐Lindenberg, A., Dickson, S. L., Millan, M. J., & Knudsen, G. M. (2022) · Neuroscience Applied · doi:10.1016/j.nsa.2022.100103 · Cited by 6
“Several studies have shown the success of this approach: for example; diagnostic classi fi cation in disorders such as ADHD (Kuang et al., 2014), schizophrenia (Kim et al., 2016), stroke (Sirsat et al., 2020), depression (Cao et al., 2017), or PTSD (Banerjee et al., 2017).”
Advancement Of Deep Learning In Big Data And Distributed Systems
Ahmed, A. S., Abood, M. S., & Hamdi, M. M. (2021) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora52670.2021.9461274 · Cited by 5
“intelligence for games, and many other areas such as online social media platforms or sensor-based data from smartphones and mobile devices [5-12].”
BackgroundA Review on Mood Assessment Using Smartphones
Sarsenbayeva, Z., Fleming, C., Tag, B., Withana, A. I., van Berkel, N., & McEwan, A. L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42283-6_22 · Cited by 5
Effectiveness of Deep Neural Network Model in Typing-based Emotion Detection on Smartphones
Ghosh, S., Ganguly, N., Mitra, B., & De, P. (2018) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3241539.3267761 · Cited by 5
Guo, L. Z., Hua, L., Jia, R., Fang, F., Zhao, B., & Cui, B. (2020) · Proceedings of the VLDB Endowment · doi:10.14778/3430915.3430922 · Cited by 5
“In these studies, the usage history is used as features for machine learning models and the targeted user state varies for each study, such as emotion state [26], user trait [22], and mental health [1].”
Method
Metadata
- Authors
- Cao, B., Zheng, L., Zhang, C., Yu, P. S., Piscitello, A., Zulueta, J., Ajilore, O., Ryan, K., & Leow, A. D.
- Affiliations
- University of Illinois Chicago (US)
- University of Illinoisat Chicago, Chicago, IL, USA
- University of Michigan (US)
- ORCID
- Venue
- Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2017-08-04
- Pages
- 747-755
- OpenAlex
- W2744939564
- Cited by
- 145
- References
- 61
- Citations by year
- 2026: 6 · 2025: 9 · 2024: 11 · 2023: 10 · 2022: 21 · 2021: 28 · 2020: 23 · 2019: 20 · 2018: 17
- FWCI
- 18.87
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (IIS-1526499 and CNS-1626432)
- National Natural Science Foundation of China (61672313)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Mental Health Research Topics
- Keywords
- mood prediction, mobile phone metadata, bipolar disorder, depression severity, decision fusion, multi-view fusion, mental health monitoring
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
