scholarly journals Deep Learning With Anaphora Resolution for the Detection of Tweeters With Depression: Algorithm Development and Validation Study

10.2196/19824 ◽  
2021 ◽  
Vol 8 (8) ◽  
pp. e19824
Author(s):  
Akkapon Wongkoblap ◽  
Miguel A Vadillo ◽  
Vasa Curcin
Keyword(s):  
Mental Health ◽  
Deep Learning ◽  
Predictive Models ◽  
Mental Health Problems ◽  
Multiple Instance Learning ◽  
Learning Models ◽  
Data Set ◽  
User Classification ◽  
Textual Content ◽  
Promising Source

Background Mental health problems are widely recognized as a major public health challenge worldwide. This concern highlights the need to develop effective tools for detecting mental health disorders in the population. Social networks are a promising source of data wherein patients publish rich personal information that can be mined to extract valuable psychological cues; however, these data come with their own set of challenges, such as the need to disambiguate between statements about oneself and third parties. Traditionally, natural language processing techniques for social media have looked at text classifiers and user classification models separately, hence presenting a challenge for researchers who want to combine text sentiment and user sentiment analysis. Objective The objective of this study is to develop a predictive model that can detect users with depression from Twitter posts and instantly identify textual content associated with mental health topics. The model can also address the problem of anaphoric resolution and highlight anaphoric interpretations. Methods We retrieved the data set from Twitter by using a regular expression or stream of real-time tweets comprising 3682 users, of which 1983 self-declared their depression and 1699 declared no depression. Two multiple instance learning models were developed—one with and one without an anaphoric resolution encoder—to identify users with depression and highlight posts related to the mental health of the author. Several previously published models were applied to our data set, and their performance was compared with that of our models. Results The maximum accuracy, F1 score, and area under the curve of our anaphoric resolution model were 92%, 92%, and 90%, respectively. The model outperformed alternative predictive models, which ranged from classical machine learning models to deep learning models. Conclusions Our model with anaphoric resolution shows promising results when compared with other predictive models and provides valuable insights into textual content that is relevant to the mental health of the tweeter.

scholarly journals Deep Learning With Anaphora Resolution for the Detection of Tweeters With Depression: Algorithm Development and Validation Study (Preprint)

2020 ◽  
Author(s):  
Akkapon Wongkoblap ◽  
Miguel A Vadillo ◽  
Vasa Curcin
Keyword(s):  
Mental Health ◽  
Deep Learning ◽  
Predictive Models ◽  
Mental Health Problems ◽  
Multiple Instance Learning ◽  
Learning Models ◽  
Data Set ◽  
User Classification ◽  
Textual Content ◽  
Promising Source

BACKGROUND Mental health problems are widely recognized as a major public health challenge worldwide. This concern highlights the need to develop effective tools for detecting mental health disorders in the population. Social networks are a promising source of data wherein patients publish rich personal information that can be mined to extract valuable psychological cues; however, these data come with their own set of challenges, such as the need to disambiguate between statements about oneself and third parties. Traditionally, natural language processing techniques for social media have looked at text classifiers and user classification models separately, hence presenting a challenge for researchers who want to combine text sentiment and user sentiment analysis. OBJECTIVE The objective of this study is to develop a predictive model that can detect users with depression from Twitter posts and instantly identify textual content associated with mental health topics. The model can also address the problem of anaphoric resolution and highlight anaphoric interpretations. METHODS We retrieved the data set from Twitter by using a regular expression or stream of real-time tweets comprising 3682 users, of which 1983 self-declared their depression and 1699 declared no depression. Two multiple instance learning models were developed—one with and one without an anaphoric resolution encoder—to identify users with depression and highlight posts related to the mental health of the author. Several previously published models were applied to our data set, and their performance was compared with that of our models. RESULTS The maximum accuracy, F1 score, and area under the curve of our anaphoric resolution model were 92%, 92%, and 90%, respectively. The model outperformed alternative predictive models, which ranged from classical machine learning models to deep learning models. CONCLUSIONS Our model with anaphoric resolution shows promising results when compared with other predictive models and provides valuable insights into textual content that is relevant to the mental health of the tweeter.

scholarly journals Deep Learning Predictive Models for Terminal Call Rate Prediction during the Warranty Period

2020 ◽  
Vol 11 (2) ◽  
pp. 36-50
Author(s):  
Aljaž Ferencek ◽  
Davorin Kofjač ◽  
Andrej Škraba ◽  
Blaž Sašek ◽  
Mirjana Kljajić Borštnar
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Predictive Models ◽  
Discrete Event ◽  
Quality Data ◽  
Call Rate ◽  
Learning Models ◽  
Data Set ◽  
Warranty Period ◽  
And Performance

AbstractBackground: This paper addresses the problem of products’ terminal call rate (TCR) prediction during the warranty period. TCR refers to the information on the amount of funds to be reserved for product repairs during the warranty period. So far, various methods have been used to address this problem, from discrete event simulation and time series, to machine learning predictive models.Objectives: In this paper, we address the above named problem by applying deep learning models to predict terminal call rate.Methods/Approach: We have developed a series of deep learning models on a data set obtained from a manufacturer of home appliances, and we have analysed their quality and performance.Results: Results showed that a deep neural network with 6 layers and a convolutional neural network gave the best results.Conclusions: This paper suggests that deep learning is an approach worth exploring further, however, with the disadvantage being that it requires large volumes of quality data.

scholarly journals Potential value of the current mental health monitoring of children in state care in England

BJPsych Open ◽  
2018 ◽  
Vol 4 (6) ◽  
pp. 486-491 ◽  
Author(s):  
Christine Cocker ◽  
Helen Minnis ◽  
Helen Sweeting
Keyword(s):  
Mental Health ◽  
Missing Data ◽  
Mental Health Problems ◽  
Population Level ◽  
Cross Sectional ◽  
Data Set ◽  
Looked After Children ◽  
Education Data ◽  
Sample Attrition ◽  
Aggregate Population

BackgroundRoutine screening to identify mental health problems in English looked-after children has been conducted since 2009 using the Strengths and Difficulties Questionnaire (SDQ).AimsTo investigate the degree to which data collection achieves screening aims (identifying scale of problem, having an impact on mental health) and the potential analytic value of the data set.MethodDepartment for Education data (2009–2017) were used to examine: aggregate, population-level trends in SDQ scores in 4/5- to 16/17-year-olds; representativeness of the SDQ sample; attrition in this sample.ResultsMean SDQ scores (around 50% ‘abnormal’ or ‘borderline’) were stable over 9 years. Levels of missing data were high (25–30%), as was attrition (28% retained for 4 years). Cross-sectional SDQ samples were not representative and longitudinal samples were biased.ConclusionsMental health screening appears justified and the data set has research potential, but the English screening programme falls short because of missing data and inadequate referral routes for those with difficulties.Declaration of interestNone.

Parsing of Urban Facades from 3D Point Clouds Based on a Novel Multi-View Domain

2021 ◽  
Vol 87 (4) ◽  
pp. 283-293
Author(s):  
Wei Wang ◽  
Yuan Xu ◽  
Yingchao Ren ◽  
Gang Wang
Keyword(s):  
Deep Learning ◽  
Prior Knowledge ◽  
Performance Improvement ◽  
Data Distribution ◽  
Point Clouds ◽  
Learning Models ◽  
Data Set ◽  
3D Point Clouds ◽  
Segmentation Accuracy ◽  
The Mean

Recently, performance improvement in facade parsing from 3D point clouds has been brought about by designing more complex network structures, which cost huge computing resources and do not take full advantage of prior knowledge of facade structure. Instead, from the perspective of data distribution, we construct a new hierarchical mesh multi-view data domain based on the characteristics of facade objects to achieve fusion of deep-learning models and prior knowledge, thereby significantly improving segmentation accuracy. We comprehensively evaluate the current mainstream method on the RueMonge 2014 data set and demonstrate the superiority of our method. The mean intersection-over-union index on the facade-parsing task reached 76.41%, which is 2.75% higher than the current best result. In addition, through comparative experiments, the reasons for the performance improvement of the proposed method are further analyzed.

Historical Trauma, Ethnic Experience, and Mental Health in a Sample of Urban American Indians

2019 ◽  
Vol 26 (2) ◽  
pp. 145-156
Author(s):  
Nicholas Guenzel ◽  
Leeza Struwe
Keyword(s):  
Mental Health ◽  
American Indians ◽  
Mental Health Problems ◽  
Psychological Symptoms ◽  
Historical Trauma ◽  
Poor Mental Health ◽  
Self Report ◽  
Data Set ◽  
Effective Care ◽  
Mainstream Society

BACKGROUND: Historical trauma (HT) among American Indians (AIs) has been linked with poor mental health but has been inadequately studied among urban populations. OBJECTIVES: The purpose of this study was to describe historical trauma, historical loss associated thoughts, ethnic experience, and psychological symptoms among a population of urban AIs. METHOD: This was a mixed methods study. In addition to focus groups, survey participants were administered the Historical Losses Scale, the Historical Losses Associated Symptoms Scale, the Scale of Ethnic Experience, and the Achenbach System of Empirically Based Assessment Adult Self-Report. Rates of psychological symptoms were compared with matched controls from a normative data set. RESULTS: Participants reported a strong sense of ethnic identity, a moderate desire to associate with other AIs, moderate comfort within mainstream society, and moderately high perceived discrimination. The most common HT themes were loss of culture, respect by children of traditional ways, and language. Compared with controls, participants had higher rates of aggressive behavior, substance use, thought problems, and obsessive symptoms, but some of these issues are likely explained by cultural factors. A greater number of participants met the clinical threshold for multiple problems compared with controls. CONCLUSIONS: This sample of AIs reported frequent experiences of discrimination. HT is a significant factor in the lives of many urban AIs who also have significantly higher rates of a number of mental health problems. Providers must be aware of these issues to provide the most effective care to AIs.

scholarly journals Prediction of EGFR Mutation Status Based on 18F-FDG PET/CT Imaging Using Deep Learning-Based Model in Lung Adenocarcinoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Guotao Yin ◽  
Ziyang Wang ◽  
Yingchao Song ◽  
Xiaofeng Li ◽  
Yiwen Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Lung Adenocarcinoma ◽  
Fdg Pet ◽  
Egfr Mutation ◽  
Learning Models ◽  
Data Set ◽  
Mutation Status ◽  
Pet Ct ◽  
Testing Data ◽  
Fdg Pet Ct

ObjectiveThe purpose of this study was to develop a deep learning-based system to automatically predict epidermal growth factor receptor (EGFR) mutant lung adenocarcinoma in 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT).MethodsThree hundred and one lung adenocarcinoma patients with EGFR mutation status were enrolled in this study. Two deep learning models (SECT and SEPET) were developed with Squeeze-and-Excitation Residual Network (SE-ResNet) module for the prediction of EGFR mutation with CT and PET images, respectively. The deep learning models were trained with a training data set of 198 patients and tested with a testing data set of 103 patients. Stacked generalization was used to integrate the results of SECT and SEPET.ResultsThe AUCs of the SECT and SEPET were 0.72 (95% CI, 0.62–0.80) and 0.74 (95% CI, 0.65–0.82) in the testing data set, respectively. After integrating SECT and SEPET with stacked generalization, the AUC was further improved to 0.84 (95% CI, 0.75–0.90), significantly higher than SECT (p<0.05).ConclusionThe stacking model based on 18F-FDG PET/CT images is capable to predict EGFR mutation status of patients with lung adenocarcinoma automatically and non-invasively. The proposed model in this study showed the potential to help clinicians identify suitable advanced patients with lung adenocarcinoma for EGFR‐targeted therapy.

scholarly journals Sentiment Analysis of Film Reviews Based on BI-GRU +Attention+Capsule Fusion

2021 ◽  
Author(s):  
zhifei hu
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Film Review ◽  
The Other ◽  
Learning Models ◽  
Analysis Model ◽  
Fusion Model ◽  
Data Set ◽  
Analysis Task ◽  
Film Reviews

In this paper, a sentiment analysis model based on the bi-directional GRU, Attention and Capusle fusion of BI-GRU+Attention+Capsule was designed and implemented based on the sentiment analysis task of the open film review data set IMDB, and combined with the bi-directional GRU, Attention and Capsule. It is compared with six deep learning models, such as LSTM, CNN, GRU, BI-GRU, CNN+GRU and GRU+CNN. The experimental results show that the accuracy of the BI-GRU model combined with Attention and Capusule is higher than the other six models, and the accuracy of the GRU+CNN model is higher than that of the CNN+GRU model, and the accuracy of the CNN+GRU model is higher than that of the CNN model. The accuracy of CNN model was successively higher than that of LSTM, BI-GRU and GRU model. The fusion model of BI-GRU +Attention+Capsule adopted in this paper has the highest accuracy among all the models. In conclusion, the fusion model of BI-GRU+Attention+Capsule effectively improves the accuracy of text sentiment classification.<br>

scholarly journals The influence of training sample size on the accuracy of deep learning models for the prediction of soil properties with near-infrared spectroscopy data

SOIL ◽  
2020 ◽  
Vol 6 (2) ◽  
pp. 565-578
Author(s):  
Wartini Ng ◽  
Budiman Minasny ◽  
Wanderson de Sousa Mendes ◽  
José Alexandre Melo Demattê
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Soil Properties ◽  
Sample Size ◽  
Training Sample ◽  
Calibration Data ◽  
Learning Models ◽  
Data Set ◽  
Calibration Data Set ◽  
Machine Learning Models

Abstract. The number of samples used in the calibration data set affects the quality of the generated predictive models using visible, near and shortwave infrared (VIS–NIR–SWIR) spectroscopy for soil attributes. Recently, the convolutional neural network (CNN) has been regarded as a highly accurate model for predicting soil properties on a large database. However, it has not yet been ascertained how large the sample size should be for CNN model to be effective. This paper investigates the effect of the training sample size on the accuracy of deep learning and machine learning models. It aims at providing an estimate of how many calibration samples are needed to improve the model performance of soil properties predictions with CNN as compared to conventional machine learning models. In addition, this paper also looks at a way to interpret the CNN models, which are commonly labelled as a black box. It is hypothesised that the performance of machine learning models will increase with an increasing number of training samples, but it will plateau when it reaches a certain number, while the performance of CNN will keep improving. The performances of two machine learning models (partial least squares regression – PLSR; Cubist) are compared against the CNN model. A VIS–NIR–SWIR spectra library from Brazil, containing 4251 unique sites with averages of two to three samples per depth (a total of 12 044 samples), was divided into calibration (3188 sites) and validation (1063 sites) sets. A subset of the calibration data set was then created to represent a smaller calibration data set ranging from 125, 300, 500, 1000, 1500, 2000, 2500 and 2700 unique sites, which is equivalent to a sample size of approximately 350, 840, 1400, 2800, 4200, 5600, 7000 and 7650. All three models (PLSR, Cubist and CNN) were generated for each sample size of the unique sites for the prediction of five different soil properties, i.e. cation exchange capacity, organic carbon, sand, silt and clay content. These calibration subset sampling processes and modelling were repeated 10 times to provide a better representation of the model performances. Learning curves showed that the accuracy increased with an increasing number of training samples. At a lower number of samples (< 1000), PLSR and Cubist performed better than CNN. The performance of CNN outweighed the PLSR and Cubist model at a sample size of 1500 and 1800, respectively. It can be recommended that deep learning is most efficient for spectra modelling for sample sizes above 2000. The accuracy of the PLSR and Cubist model seems to reach a plateau above sample sizes of 4200 and 5000, respectively, while the accuracy of CNN has not plateaued. A sensitivity analysis of the CNN model demonstrated its ability to determine important wavelengths region that affected the predictions of various soil attributes.

Parents’ perception of children’s mental health: seeing the signs but not the problems

2018 ◽  
Vol 104 (11) ◽  
pp. 1102-1104 ◽  
Author(s):  
Li Huang ◽  
Harriet Hiscock ◽  
Kim M Dalziel
Keyword(s):  
Mental Health ◽  
Low Income ◽  
Mental Health Problems ◽  
Health Problems ◽  
Children’S Mental Health ◽  
Children's Mental Health ◽  
Income Quintile ◽  
Data Set ◽  
Nationally Representative ◽  
Low Income Families

BackgroundIt is a public heath priority to understand why many children with mental health problems fail to access mental health services. This study aims to quantify under-recognition of children’s mental health problems by parents across income quintiles.MethodsWe estimated under-recognition with parent-reported mental health problems and the Strengths and Difficulties Questionnaire (SDQ) using a nationally representative Australian data set for children aged 4–15 years with 24 269 person-wave observations.ResultsUnder-recognition was the highest in the lowest income quintile, with 11.5% of children from the lowest income quintile families who scored in the clinical range on the SDQ perceived by parents as having no mental health problems. For the highest income quintile this was 2.4%. In terms of gender and age, under-recognition was greater for boys and younger children.ConclusionsParent’s mental health literacy, especially for low-income families, warrants prioritised attention from researchers, clinicians and policymakers.

Sign in / Sign up

Export Citation Format

Share Document