Welcome to the upgraded BRAC University Institutional Repository. We are currently organizing collections after a recent system upgrade. Homepage category counters may temporarily show lower numbers while syncing, but over 27,000 repository items remain safe and accessible. Please use the search bar to find theses, scholarly outputs, and institutional documents.

Detecting self-esteem level and depressive indication due to different parenting style using supervised learning techniques

Citation

Abstract

Uprising a child is a psychological construct of parents, which is a combination of factors that evolves over time with the growth and development of the child. Parent ing style represents a set of strategies that have diverse influences on children. These approaches can create depressive symptoms in children’s minds, which can last even if they become adolescents. Moreover, these indications may affect their level of self confidence. In this research, supervised learning models are used to detect different parenting styles, depression indications of adolescents due to parenting and the level of their self-esteem. Due to the absence of publicly available data, we created our own data set of about 500 survey responses. Additionally, eleven psychological and nine linguistic attributes of Linguistic Inquiry and Word Count (LIWC) have been used to identify depression indications. Among all the supervised models, the Lo gistic Regression (LR), Gradient Boost Classifier (GBC) and Bi-Directional LSTM (Bi-LSTM) provide better results than other models. This research is capable of helping the parents to know their children’s psychology in a better way and make them have a more profound discussion on practical life.

LC Subject Headings

Description

Cataloged from PDF version of thesis.
Includes bibliographical references (pages 37-39).
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.

Publisher Link

Type

Thesis