Deep Learning Approach for Loneliness Identification from Speech using DNN-LSTM

Perceived loneliness and social isolation have been on the rise over the past decade, especially in countries with rapidly ageing populations and, most notably, as a result of the stress of dealing with the COVID-19 outbreak over the past two years. By using a natural language processing (NLP) approach to quantify sentiment and variables that signal loneliness in transcribed spoken text of older persons, this paper investigates the use of deep learning technology in the evaluation of interviews on loneliness. We conducted loneliness state detection using Deep Neural Network (DNN) and Long Short-Term Memory (LSTM). Participants who were lonely and those who weren't were compared (using both qualitative and quantitative measures). Individuals who were lonelier (as determined by qualitative measures) took longer to respond to questions about their loneliness and expressed more grief in their answers. When asked about loneliness, more women than men admitted it during the qualitative interview. When responding, men were more likely to utilize expressions of dread and happiness. When trained on textual data, DNN models were 100% accurate at predicting qualitative loneliness and LSTM models were 75.42% accurate at predicting loneliness on textual data.