{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308337324"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308337324","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Propagandos ir dezinformacijos tekstų plitimo socialiniuose tinkluose tyrimas /","abstract":"The spread of propaganda and disinformation texts on social media is a relevant and complex contemporary issue significantly influenced by social media bots. This thesis analyzes the types of social bots and their detection methods, distinguishing the main groups of methods: machine learning, deep learning, graph-based, and expert-based methods. During the research, the level of bot prevalence on the social network X (Twitter) was evaluated using “Botometer X” across two propaganda-related and, for comparison, two non-propaganda hashtags. The results showed that bot prevalence under propaganda hashtags reached 13% and 8.7%, while under non-propaganda hashtags it reached 4.8% and 11.6%. When evaluating only currently active accounts (not deleted or suspended for violating platform rules), these indicators decreased. Applying the activity-based “intensive automation” method produced higher bot prevalence estimates, especially in propaganda-related hashtags. The calculated average bot prevalence level demonstrated that bot prevalence in propaganda hashtags was higher (18% and 14.1%) than in non propaganda hashtags (5.7% and 7.8%). The obtained results suggest that potentially automated accounts are used more frequently in propaganda-related discussions on social media, while different bot detection methods produce inconsistent results; therefore, a combination of multiple methods is necessary for more reliable evaluation.","abstract_html":"The spread of propaganda and disinformation texts on social media is a relevant and complex contemporary issue significantly influenced by social media bots. This thesis analyzes the types of social bots and their detection methods, distinguishing the main groups of methods: machine learning, deep learning, graph-based, and expert-based methods. During the research, the level of bot prevalence on the social network X (Twitter) was evaluated using “Botometer X” across two propaganda-related and, for comparison, two non-propaganda hashtags. The results showed that bot prevalence under propaganda hashtags reached 13% and 8.7%, while under non-propaganda hashtags it reached 4.8% and 11.6%. When evaluating only currently active accounts (not deleted or suspended for violating platform rules), these indicators decreased. Applying the activity-based “intensive automation” method produced higher bot prevalence estimates, especially in propaganda-related hashtags. The calculated average bot prevalence level demonstrated that bot prevalence in propaganda hashtags was higher (18% and 14.1%) than in non propaganda hashtags (5.7% and 7.8%). The obtained results suggest that potentially automated accounts are used more frequently in propaganda-related discussions on social media, while different bot detection methods produce inconsistent results; therefore, a combination of multiple methods is necessary for more reliable evaluation.","abstract_has_math":false,"creators":["Karvelis, Andrius,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:59Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308337324&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308337324&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308337324","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Karvelis, Andrius,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308337324/308337324.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308337324&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The spread of propaganda and disinformation texts on social media is a relevant and complex contemporary issue significantly influenced by social media bots. This thesis analyzes the types of social bots and their detection methods, distinguishing the main groups of methods: machine learning, deep learning, graph-based, and expert-based methods. During the research, the level of bot prevalence on the social network X (Twitter) was evaluated using “Botometer X” across two propaganda-related and, for comparison, two non-propaganda hashtags. The results showed that bot prevalence under propaganda hashtags reached 13% and 8.7%, while under non-propaganda hashtags it reached 4.8% and 11.6%. When evaluating only currently active accounts (not deleted or suspended for violating platform rules), these indicators decreased. Applying the activity-based “intensive automation” method produced higher bot prevalence estimates, especially in propaganda-related hashtags. The calculated average bot prevalence level demonstrated that bot prevalence in propaganda hashtags was higher (18% and 14.1%) than in non propaganda hashtags (5.7% and 7.8%). The obtained results suggest that potentially automated accounts are used more frequently in propaganda-related discussions on social media, while different bot detection methods produce inconsistent results; therefore, a combination of multiple methods is necessary for more reliable evaluation."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Propagandos ir dezinformacijos tekstų plitimo socialiniuose tinkluose tyrimas /","Investigating the spread of propaganda and disinformation texts in social networks."]}]}],"canonical_facts":{"dc:creator":["Karvelis, Andrius,"],"dc:date":["2026"],"dc:description":["The spread of propaganda and disinformation texts on social media is a relevant and complex contemporary issue significantly influenced by social media bots. This thesis analyzes the types of social bots and their detection methods, distinguishing the main groups of methods: machine learning, deep learning, graph-based, and expert-based methods. During the research, the level of bot prevalence on the social network X (Twitter) was evaluated using “Botometer X” across two propaganda-related and, for comparison, two non-propaganda hashtags. The results showed that bot prevalence under propaganda hashtags reached 13% and 8.7%, while under non-propaganda hashtags it reached 4.8% and 11.6%. When evaluating only currently active accounts (not deleted or suspended for violating platform rules), these indicators decreased. Applying the activity-based “intensive automation” method produced higher bot prevalence estimates, especially in propaganda-related hashtags. The calculated average bot prevalence level demonstrated that bot prevalence in propaganda hashtags was higher (18% and 14.1%) than in non propaganda hashtags (5.7% and 7.8%). The obtained results suggest that potentially automated accounts are used more frequently in propaganda-related discussions on social media, while different bot detection methods produce inconsistent results; therefore, a combination of multiple methods is necessary for more reliable evaluation."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308337324&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308337324/308337324.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Propagandos ir dezinformacijos tekstų plitimo socialiniuose tinkluose tyrimas /","Investigating the spread of propaganda and disinformation texts in social networks."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:59Z"}