Susastho adolescent Dataset_24.09.24.xlsx

A dataset for adolescents has been gathered in SRMH(Sexual, Reproductive &amp; Mental Health) domain. The aim of this dataset is to build a conversational agent in Bengali which will mitigate the lack of knowledge of the adolescent regarding these topics and would also act as a bridge to minimize the gaps and foster understanding in this target populations. The dataset is divided into 2 domains which are Sexual &amp; Reproductive and Mental Health.<br>Sexual Reproductive Health consists of a total 1966 data of which 756 were contextual. Moreover, Mental Health consists of 470 data of which 146 were contextual. These data were augmented later for a total of 7278 data of which 5849 was of Sexual Reproductive Health. The percentage of raw data for the Sexual &amp; Reproductive and Mental Health are 80.7% to 19.3% respectively. Furthermore, the percentage of augmented data for SRMH are 80.4% to 19.6% respectively. This clearly shows that we have a skewed distribution and the dataset is imbalanced. Also the data is created to act as a knowledgebase for a conversational agent.