Abstract：Practicability of Ensemble Artificial Neural Network Models for a Classification TaskAn Optimal Approach for Reproducing Classification Practices of Health Consumers Generated Text on Social Media This paper reports the classification accuracy of artificial neural networkANNmodels in reproducing health consumersclassification practices in social mediaSocial media have driven the growth of unstructured text data across domains including healthwhich motivates researchers to reconsider the epistemological approach to automated classificationThis study compared the performance of several types of ANN models and ensemble models based on classification results and the integration of multiple ANN structuresTo train these modelstwo dictionaries were employedhealth consumersterms extracted from questions and answers in the health categories of YahooAnswers and MeSH termsAll three types of individual classifiers demonstrated accuracies of around 90In particularthe fully connected ANN with two layers produced relatively higher classification performances than a convolutional neural network and long short-term memoryEnsemble models based on classification results outperformed not only the ensemble models based on the integration of heterogeneous ANN structures but also individual deep-learning modelsThe combination of questions and best answers were found to be most effective as a training dataset to build an accurate prediction modelThe findings suggest that ANN models can be an effective assistive tool in classifying online health resources generated by health consumers in natural language Collection ClassificationThe text and organizations of web resources have been mentioned many timesand how to automatically classify the content of social media related to the use of machine learning technologywhich is very similar to the librarys collection classificationNLPStudy the classification habits of healthy consumers in social mediainvolving the processing and understanding of the data generated by natural languageModel recognitionThis is the core activity of automatic classification of data extracted from social mediaMachine LearningThis article refers to classification of using an artificial neural networkANNmodelwhich is part of machine learningDeep LearningSpecifically mentioned the use of deep learning modelssuch as ANNconvolutional neural networksand long-term memory of full-connected