<Record><identifier xmlns="http://purl.org/dc/elements/1.1/">URN:NBN:SI:doc-OH048SZK</identifier><date>2025</date><creator>Taoussi, Chaimae</creator><relation>documents/doc/O/URN_NBN_SI_doc-OH048SZK_001.pdf</relation><relation>documents/doc/O/URN_NBN_SI_doc-OH048SZK_001.txt</relation><format format_type="issue">14</format><format format_type="volume">49</format><format format_type="type">article</format><format format_type="extent">str. 1-17</format><identifier identifier_type="DOI">10.31449/inf.v49i14.7451</identifier><identifier identifier_type="ISSN">1854-3871</identifier><identifier identifier_type="COBISSID">241408771</identifier><identifier identifier_type="URN">URN:NBN:SI:doc-OH048SZK</identifier><language>eng</language><publisher publisher_location="Ljubljana">Informatika</publisher><source>Informatica (Ljubljana)</source><rights>BY</rights><subject language_type_id="slv">diagnostika</subject><subject language_type_id="slv">duševno zdravje</subject><subject language_type_id="slv">globoko učenje</subject><subject language_type_id="slv">strojno učenje</subject><subject language_type_id="slv">umetna inteligenca</subject><title>Enhancing machine learning and deep learning models for depression detection</title><title>a focus on SMOTE, ROBERTa, and CNN-LSTM</title></Record>