{"id":"https://openalex.org/W4409720450","doi":"https://doi.org/10.1145/3706599.3719821","title":"Can Large Language Models Grasp Abstract Visual Concepts in Videos? A Case Study on YouTube Shorts about Depression","display_name":"Can Large Language Models Grasp Abstract Visual Concepts in Videos? A Case Study on YouTube Shorts about Depression","publication_year":2025,"publication_date":"2025-04-23","ids":{"openalex":"https://openalex.org/W4409720450","doi":"https://doi.org/10.1145/3706599.3719821"},"language":"en","primary_location":{"id":"doi:10.1145/3706599.3719821","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3706599.3719821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.05109","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082156750","display_name":"Jiaying Liu","orcid":"https://orcid.org/0000-0002-5398-1485"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiaying \"Lizzy\" Liu","raw_affiliation_strings":["School of Information, University of Texas at Austin, Austin, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0002-5398-1485","affiliations":[{"raw_affiliation_string":"School of Information, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102694132","display_name":"Yiheng Su","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiheng Su","raw_affiliation_strings":["Artificial Intelligence and Human-Centered Computing (AI&HCC) Lab, The University of Texas at Austin, Austin, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0001-8021-429X","affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Human-Centered Computing (AI&HCC) Lab, The University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":null,"display_name":"Praneel Seth","orcid":"https://orcid.org/0009-0001-4665-0776"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Praneel Seth","raw_affiliation_strings":["Computer Science Department, University of Texas at Austin, Austin, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0001-4665-0776","affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082156750"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.2665,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8750847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12214","display_name":"Media Influence and Health","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.9192143678665161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6554079651832581},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.5151704549789429},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4667890965938568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4128151535987854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4071006774902344},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.37142735719680786},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.349321573972702},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22858622670173645},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21795395016670227},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16120800375938416},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05926564335823059}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.9192143678665161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6554079651832581},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.5151704549789429},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4667890965938568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4128151535987854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4071006774902344},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.37142735719680786},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.349321573972702},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22858622670173645},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21795395016670227},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16120800375938416},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05926564335823059},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3706599.3719821","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3706599.3719821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.05109","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.05109","pdf_url":"https://arxiv.org/pdf/2503.05109","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.05109","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.05109","pdf_url":"https://arxiv.org/pdf/2503.05109","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1979290264","https://openalex.org/W2003676674","https://openalex.org/W2133665775","https://openalex.org/W2146120111","https://openalex.org/W2284264830","https://openalex.org/W2566909055","https://openalex.org/W2588050621","https://openalex.org/W2592658867","https://openalex.org/W2610332539","https://openalex.org/W2611167769","https://openalex.org/W2737677090","https://openalex.org/W2765108713","https://openalex.org/W2803769621","https://openalex.org/W2941513909","https://openalex.org/W2990138404","https://openalex.org/W3001362559","https://openalex.org/W4252849059","https://openalex.org/W4360978668","https://openalex.org/W4366548515","https://openalex.org/W4366590580","https://openalex.org/W4380319170","https://openalex.org/W4382538068","https://openalex.org/W4385567149","https://openalex.org/W4385800557","https://openalex.org/W4386908233","https://openalex.org/W4387329158","https://openalex.org/W4387606052","https://openalex.org/W4389519587","https://openalex.org/W4390038780","https://openalex.org/W4391043766","https://openalex.org/W4391136507","https://openalex.org/W4392427296","https://openalex.org/W4392736278","https://openalex.org/W4396218059","https://openalex.org/W4396832002","https://openalex.org/W4396833376","https://openalex.org/W4396833706","https://openalex.org/W4399205864","https://openalex.org/W4399362737","https://openalex.org/W4400222414","https://openalex.org/W4402671996","https://openalex.org/W4402727764","https://openalex.org/W4402780269","https://openalex.org/W4402904028","https://openalex.org/W4404331635","https://openalex.org/W4404356490","https://openalex.org/W4404782964"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2019547100","https://openalex.org/W2477150073","https://openalex.org/W2141293686"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6],"to":[7,49,60,132,142],"assist":[8],"computational":[9],"social":[10],"science":[11],"research.":[12],"While":[13],"prior":[14],"efforts":[15],"have":[16],"focused":[17],"on":[18,41],"text,":[19],"the":[20,37,89,130],"potential":[21],"of":[22,36,52,82,91,123],"leveraging":[23],"multimodal":[24,154],"LLMs":[25],"(MLLMs)":[26],"for":[27,135,140],"online":[28],"video":[29,43,124],"studies":[30,40],"remains":[31],"underexplored.":[32],"We":[33,55,77,106],"conduct":[34],"one":[35],"first":[38],"case":[39],"MLLM-assisted":[42],"content":[44],"analysis,":[45],"comparing":[46],"AI's":[47],"interpretations":[48],"human":[50,115],"understanding":[51],"abstract":[53,63],"concepts.":[54],"leverage":[56],"LLaVA-1.6":[57],"Mistral":[58],"7B":[59],"interpret":[61],"four":[62],"concepts":[64,137],"regarding":[65],"video-mediated":[66],"self-disclosure,":[67],"analyzing":[68],"725":[69],"keyframes":[70],"from":[71],"142":[72],"depression-related":[73],"YouTube":[74],"short":[75],"videos.":[76],"perform":[78],"a":[79,153],"qualitative":[80],"analysis":[81],"MLLM's":[83,95],"self-generated":[84],"explanations":[85],"and":[86,121,138],"found":[87],"that":[88],"degree":[90],"operationalization":[92],"can":[93],"influence":[94],"interpretations.":[96],"Interestingly,":[97],"greater":[98],"detail":[99],"does":[100],"not":[101],"necessarily":[102],"increase":[103],"human-AI":[104],"alignment.":[105],"also":[107],"identify":[108],"other":[109],"factors":[110],"affecting":[111],"AI":[112,150],"alignment":[113],"with":[114,149],"understanding,":[116],"such":[117],"as":[118],"concept":[119],"complexity":[120],"versatility":[122],"genres.":[125],"Our":[126],"exploratory":[127],"study":[128],"highlights":[129],"need":[131],"customize":[133],"prompts":[134],"specific":[136],"calls":[139],"researchers":[141],"incorporate":[143],"more":[144],"human-centered":[145],"evaluations":[146],"when":[147],"working":[148],"systems":[151],"in":[152],"context.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-04-24T00:00:00"}