Corpus ID: 211838254

PyNDA: Deep Learning for Psychometric Natural Language Processing

@inproceedings{Li2019PyNDADL,
  title={PyNDA: Deep Learning for Psychometric Natural Language Processing},
  author={Jingjing Li and A. Abbasi and Faizan Ahmad and Hsinchun Chen},
  year={2019}
}
SYCHOMETRICS is concerned with the measurement of knowledge, ability, attitudes, and personality traits. With the increased importance of predictive analytics at the micro-level [1], including prediction of individuals’ behaviors [2], accurate and timely measurement of psychometrics has become of paramount importance. In health settings, psychometric measures, including health numeracy, subjective literacy, and perceptions of trust and anxiety related to physicians, have been shown to have a… Expand

Figures and Tables from this paper

Constructing a Testbed for Psychometric Natural Language Processing
TLDR
The efforts to construct a corpus for psychometric natural language processing (NLP) are described and a multi-step process to align user text with their survey-based response items is discussed and an overview of the resulting testbed is provided. Expand
UNLOCKING OUR BEHAVIORAL KNOWLEDGE INHERITANCE THROUGH ONTOLOGY LEARNING: A DESIGN FRAMEWORK, AN INSTANTIATION, AND A RANDOMIZED EXPERIMENT
The accumulated literature base in the behavioral sciences represents the most significant source of knowledge about human behavior, yet the same literature has grown beyond human comprehension,Expand

References

SHOWING 1-10 OF 52 REFERENCES
A Deep Learning Architecture for Psychometric Natural Language Processing
TLDR
A deep learning architecture to extract psychometric dimensions from user-generated texts, PyNDA, which markedly outperforms traditional feature-based classifiers as well as the state-of-the-art deep learning architectures. Expand
Deep Learning for Psychometric NLP
Psychometric measures reflecting people’s knowledge, ability, attitudes and personality traits are critical for many real-world applications, such as e-commerce, healthcare, and cybersecurity.Expand
Development and Validation of the Numeracy Understanding in Medicine Instrument Short Form
TLDR
Results show that the short form of the NUMi is a reliable and valid measure of health numeracy feasible for use in clinical and research settings. Expand
The grounded psychometric development and initial validation of the Health Literacy Questionnaire (HLQ)
TLDR
The HLQ covers 9 conceptually distinct areas of health literacy to assess the needs and challenges of a wide range of people and organisations and is likely to be useful in surveys, intervention evaluation, and studies of theneeds and capabilities of individuals. Expand
An RNN Architecture with Dynamic Temporal Matching for Personalized Predictions of Parkinson's Disease
TLDR
A deep model is proposed that directly learns patient similarity from longitudinal and multi-modal patient records with an Recurrent Neural Network (RNN) architecture, which learns the similarity between two longitudinal patient record sequences through dynamically matching temporal patterns in patient sequences. Expand
When Are Tree Structures Necessary for Deep Learning of Representations?
TLDR
This paper benchmarks recursive neural models against sequential recurrent neural models, enforcing applesto-apples comparison as much as possible, and introduces a method for allowing recurrent models to achieve similar performance: breaking long sentences into clause-like units at punctuation and processing them separately before combining. Expand
Affect Analysis of Web Forums and Blogs Using Correlation Ensembles
TLDR
A brief case study was conducted to illustrate the utility of the features and techniques for affect analysis of large archives of online discourse, and showed that learned n-grams were more effective than lexicon-based affect representations. Expand
Adversarial Multi-task Learning for Text Classification
TLDR
This paper proposes an adversarial multi-task learning framework, alleviating the shared and private latent feature spaces from interfering with each other, and conducts extensive experiments on 16 different text classification tasks, which demonstrates the benefits of the approach. Expand
Microblog Dimensionality Reduction—A Deep Learning Approach
TLDR
Deep networks are applied to map the high-dimensional representations of microblog texts to low-dimensional representation to improve the result of dimensionality reduction, and the semantic similarity derived from two types of micro blogspecific information, namely the retweet relationship and hashtags is taken. Expand
A C-LSTM Neural Network for Text Classification
TLDR
C-LSTM is a novel and unified model for sentence representation and text classification that outperforms both CNN and LSTM and can achieve excellent performance on these tasks. Expand
...
1
2
3
4
5
...