Effective Deep Neural Network Method based Sentimental Analysis for Social Media Health Care Information

Main Article Content

D. Sasikala, et. al.


With the advent of natural language processing and machine learning techniques, Sentimental Analysis (SA) is receiving attention among various communities due to interpreting and classifying emotions from subjective data. The way of categorizing the emotions as positive, negative, and neutral enables the brand providers to know about their intention and reaction to their products. Existing researches have been focused on text summarization, feature reduction, and sentiment prediction separately. In this paper, all the approaches are integrated to provide a novel sentimental analysis framework for classifying the patients' emotions towards the medical facility through Twitter, Facebook, and other social media. The main aim of the work is manifold. The proposed paper performs preprocessing at the outset, which includes word segmentation, tokenization, TF-IDF, and stemming. First, the text summarization is performed by applying query-based summarization, which adopts a Deep Neural Network (DNN) for encoding the input data encompassing text and icon to convert into a fixed size at the final state, followed by decoding the encoded text and icon using the unidirectional DNN for creating the summary of the input document. Second, to improve scalability, feature reduction is performed using the effective Genetic Algorithm. The proposed system is experimented with using the real-time datasets from social media platforms to analyze the proposed healthcare sentimental analysis model. The parameters such as accuracy, F-score, recall rate, and precision are chosen to analyze the performance against existing sentimental analysis models.


Download data is not yet available.


Metrics Loading ...

Article Details

How to Cite
et. al., D. S. . (2021). Effective Deep Neural Network Method based Sentimental Analysis for Social Media Health Care Information. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(10), 1883–1889. Retrieved from https://turcomat.org/index.php/turkbilmat/article/view/4674