Estimation of depression levels using Hamilton Test
Description
This Dataset presents data for the estimation of depression level estimation based in factor psychological and life experiences. The data contains 23 attributes and 347records, the records are labelled with the class variable not depressed, light/minor depression, moderate depression, severe depression, very severe depression that indicate the respective level of depression. 46% of the data was generated synthetically using the Weka tool and the SMOTE filter, 54% of the data was collected directly from users through a web platform. This data can be used to generate intelligent computational tools to identify the depression level of an individual and to build recommender systems that monitor depression levels.
Files
Steps to reproduce
For the construction process of the data set, it is based on the questions posed in the Hamilton Test along with additional questions such as age, educational level, occupation, and salary income range. Based on the above, a web form was designed for the data collection. The collected data was exported to a CSV file and processed using Python with the Pandas libraries, after data cleaning and transformation, a new CSV file was created with the processed data and a file was created in ARFF format so that it can be used in data analysis tools such as Weka.