BackgroundGlobally there is a rapid increase in prison population, and one out of nine inmates suffers from mental disorders like depression. In Ethiopia, although a mental health strategy is in place, little attention is given to prisoners and studies which focus on depression among prisoners are still scarce. The aim of this study was to assess the prevalence of depression and factors associated with it among prisoners.MethodAcross-sectional study was conducted from October 5 to 28, 2016 in Bahir Dar city. Simple random sampling technique was used to select 402 prisoners. Depression was measured using Patient Health Questionnaire, nine item version (PHQ-9) at a cut point of five. Data on socio-demographic characteristics, behavioral factors, perceived general health, and prison situation variables were collected using structured questionnaire. The data were collected by trained interviewers. SPSS version 20 was used to analyze the data. Binary logistic regression was used to identify predictors of depression.ResultThe prevalence of depression was 45.5% (95%CI: 40.5–50.5%). In the final model, having children [Adjusted Odds Ratio (AOR) = 2.48; 95%CI: 1.60–3.83], health satisfaction rated as moderate [AOR = 3.20; 95%CI: 1.12–9.00] or dissatisfied [AOR = 1.63; 95%CI: 1.02–2.62] compared to satisfied, being sentenced for more than 5 years [AOR = 2.31; 95%CI: 1.01–5.25] or 1–5 years [AOR = 3.04; 95%CI: 1.2–7.71] were positively associated with depression.ConclusionHigh prevalence of depression was found among prisoners. Those with poor general health, long years of imprisonment, and concerns of children were the most vulnerable. Strengthening mental health services of prisons is critically required.

This research aims to develop a sentiment analysis system specifically designed for the Amharic language. The study employs four deep learning algorithms to achieve this goal: Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), Gated Recurrent Unit (GRU), and a combination of CNN and BiLSTM. The CNN algorithm is utilized for its effectiveness in extracting relevant features from the input data. By applying filters and pooling operations, the CNN can identify important patterns and structures within the Amharic text. The BiLSTM algorithm is chosen for its ability to process sequential information by considering both past and future contexts. It incorporates a memory cell that enables the model to retain important information and understand the dependencies between different parts of the text. Additionally, the GRU algorithm is employed as it offers similar capabilities to BiLSTM but with fewer computational requirements. This allows for more efficient processing without sacrificing performance. The experimental results obtained from the sentiment analysis system indicate that the combination of CNN and BiLSTM yields promising outcomes. The system achieved an accuracy rate of 91.60%, demonstrating its ability to correctly classify sentiments expressed in Amharic text. Furthermore, the precision rate of 90.47% indicates a high level of accuracy in identifying positive and negative sentiments, while the recall rate of 93.91% suggests that the system effectively captures relevant sentiment instances. In summary, this study successfully designs a sentiment analysis system specifically tailored for the Amharic language. By leveraging the capabilities of deep learning algorithms such as CNN, BiLSTM, and GRU, the system demonstrates strong performance in accurately classifying sentiments expressed in Amharic text, as evidenced by the achieved accuracy, precision, and recall rates.