{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T05:22:58Z","timestamp":1768022578461,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3715070.3749225","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T05:55:41Z","timestamp":1760680541000},"page":"199-203","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ConCaV: Confusion-triggered Captioning for Video Calls"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9601-0064","authenticated-orcid":false,"given":"Melanie","family":"Heck","sequence":"first","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6166-190X","authenticated-orcid":false,"given":"Alexander","family":"Bunz","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4173-5052","authenticated-orcid":false,"given":"Omar","family":"Al Kadri","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5050-2875","authenticated-orcid":false,"given":"Mohamad","family":"Alkadre","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4029-8708","authenticated-orcid":false,"given":"Rang","family":"Omar","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2818-6926","authenticated-orcid":false,"given":"Robert","family":"Blaauw","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9036-1410","authenticated-orcid":false,"given":"Christian","family":"Becker","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"Emotion AI 101: All About Emotion Detection and Affectiva\u2019s Emotion Metrics","year":"2017","unstructured":"Affectiva. 2017. Emotion AI 101: All About Emotion Detection and Affectiva\u2019s Emotion Metrics. Affectiva. Retrieved February 28, 2025 from https:\/\/blog.affectiva.com\/emotion-ai-101-all-about-emotion-detection-and-affectivas-emotion-metrics"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/170035.170072"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284869"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.600"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"M. Benzeghiba R. De Mori O. Deroo S. Dupont T. Erbes D. Jouvet L. Fissore P. Laface A. Mertins C. Ris R. Rose V. Tyagi and C. Wellekens. 2007. Automatic speech recognition and speech variability: A review. Speech Communication 49 10 (2007) 763\u2013786. 10.1016\/j.specom.2007.02.006","DOI":"10.1016\/j.specom.2007.02.006"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042673"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW.2019.8925037"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Alessia Cogo and Marie-Luise Pitzl. 2016. Pre-empting and signalling non-understanding in ELF. ELT journal 70 3 (2016) 339\u2013345.","DOI":"10.1093\/elt\/ccw015"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998268"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Sidney\u00a0K. D\u2019Mello Scotty\u00a0D. Craig and Art\u00a0C. Graesser. 2009. Multimethod Assessment of Affective Experience and Expression during Deep Learning. International Journal of Learning Technology 4 3\/4 (2009) 165\u2013187. 10.1504\/IJLT.2009.028805","DOI":"10.1504\/IJLT.2009.028805"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Paul Ekman and Wallace\u00a0V. Friesen. 1971. Constants across cultures in the face and emotion. Journal of Personality and Social Psychology 17 (1971) 124\u2013129. Issue 2. 10.1037\/h0030377","DOI":"10.1037\/h0030377"},{"key":"e_1_3_3_1_14_2","volume-title":"Facial action coding system: Manual","author":"Ekman Paul","year":"1978","unstructured":"Paul Ekman and Wallace\u00a0V. Friesen. 1978. Facial action coding system: Manual. Consulting Psychologists Press, Palo Alto, CA, USA."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Aida Etemadi. 2012. Effects of bimodal subtitling of English movies on content comprehension and vocabulary recognition. International Journal of English Linguistics 2 1 (2012) 239.","DOI":"10.5539\/ijel.v2n1p239"},{"key":"e_1_3_3_1_16_2","volume-title":"Facial Action Coding System (FACS) \u2013 A Visual Guidebook","author":"Farnsworth Bryn","year":"2022","unstructured":"Bryn Farnsworth. 2022. Facial Action Coding System (FACS) \u2013 A Visual Guidebook. iMotions. Retrieved February 28, 2025 from https:\/\/imotions.com\/blog\/learning\/research-fundamentals\/facial-action-coding-system\/#emotions-and-action-units"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3311823.3311865"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Morton\u00a0Ann Gernsbacher. 2015. Video captions benefit everyone. Policy insights from the behavioral and brain sciences 2 1 (2015) 195\u2013202.","DOI":"10.1177\/2372732215602130"},{"key":"e_1_3_3_1_19_2","volume-title":"Use captions in a meeting","year":"2025","unstructured":"Google. 2025. Use captions in a meeting. Google. Retrieved February 28, 2025 from https:\/\/support.google.com\/meet\/answer\/9300310"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Abdolmajid Hayati and Firooz Mohmedi. 2011. The effect of films with and without subtitles on listening comprehension of EFL learners. British Journal of Educational Technology 42 1 (2011) 181\u2013192. 10.1111\/j.1467-8535.2009.01004.x","DOI":"10.1111\/j.1467-8535.2009.01004.x"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614142"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2011.5722919"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW52867.2021.9666351"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","unstructured":"Christian\u00a0G. Kohler Travis Turner Neal\u00a0M. Stolar Warren\u00a0B. Bilker Colleen\u00a0M. Brensinger Raquel\u00a0E. Gur and Ruben\u00a0C. Gur. 2004. Differences in facial expressions of four universal emotions. Psychiatry Research 128 3 (2004) 235\u2013244. 10.1016\/j.psychres.2004.07.003","DOI":"10.1016\/j.psychres.2004.07.003"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","unstructured":"Mukta Kulkarni. 2019. Digital accessibility: Challenges and opportunities. IIMB Management Review 31 1 (2019) 91\u201398. 10.1016\/j.iimb.2018.05.009","DOI":"10.1016\/j.iimb.2018.05.009"},{"key":"e_1_3_3_1_26_2","volume-title":"OpenFace 2.2.0: a facial behavior analysis toolkit","author":"Lab CMU\u00a0MultiComp","year":"2019","unstructured":"CMU\u00a0MultiComp Lab. 2019. OpenFace 2.2.0: a facial behavior analysis toolkit. Carnegie Mellon University, Pittsburgh, PA, USA. Retrieved Febraury 28, 2025 from https:\/\/github.com\/TadasBaltrusaitis\/OpenFace"},{"key":"e_1_3_3_1_27_2","volume-title":"Zoom\u2019s Auto-Generated Captions Available to All Free Users","author":"Larkin Theresa","year":"2021","unstructured":"Theresa Larkin. 2021. Zoom\u2019s Auto-Generated Captions Available to All Free Users. Zoom. Retrieved February 28, 2025 from https:\/\/blog.zoom.us\/zoom-auto-generated-captions\/"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2851613.2851681"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Kim McDonough Rachael Lindberg Pavel Trofimovich and Oguzhan Tekin. 2023. The visual signature of non-understanding: A systematic replication of McDonough Trofimovich Lu and Abashidze (2019). Language Teaching 56 1 (2023) 113\u2013127. 10.1017\/S0261444821000197","DOI":"10.1017\/S0261444821000197"},{"key":"e_1_3_3_1_30_2","volume-title":"View live transcription in a Teams meeting","year":"2025","unstructured":"Microsoft. 2025. View live transcription in a Teams meeting. Microsoft. Retrieved February 28, 2025 from https:\/\/support.microsoft.com\/en-us\/office\/dc1a8f23-2e20-4684-885e-2152e06a4a8b"},{"key":"e_1_3_3_1_31_2","unstructured":"Karla\u00a0Kmetz Morris Casey Frechette Lyman Dukes\u00a0III Nicole Stowell Nicole\u00a0Emert Topping and David Brodosi. 2016. Closed Captioning Matters: Examining the Value of Closed Captions for \"All\" Students. Journal of Postsecondary Education and Disability 29 3 (2016) 231\u2013238."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Elisa Perego Fabio\u00a0Del Missier Marco Porta and Mauro Mosconi. 2010. The cognitive effectiveness of subtitle processing. Media Psychology 13 3 (2010) 243\u2013272. 10.1080\/15213269.2010.502873","DOI":"10.1080\/15213269.2010.502873"},{"key":"e_1_3_3_1_33_2","series-title":"(INTERACT \u201919)","first-page":"293","volume-title":"Human-Computer Interaction","author":"Schneegass Christina","year":"2019","unstructured":"Christina Schneegass, Thomas Kosch, and Heinrich Schmidt, Albrechtand\u00a0Hussmann. 2019. Investigating the Potential of EEG for Implicit Detection of Unknown Words for Foreign Language Learning. In Human-Computer Interaction(INTERACT \u201919). Springer International Publishing, Cham, 293\u2013313."},{"key":"e_1_3_3_1_34_2","unstructured":"Carli Spina. 2021. Captions. Library Technology Reports 57 3 (2021) 7\u201312."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2008.4563182"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Paula Winke Susan Gass and Tetyana Sydorenko. 2010. The Effects of Captioning Videos Used for Foreign Language Listening Activities. Language Learning and Technology 14 (2010) 22\u00a0pages.","DOI":"10.64152\/10125\/44203"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Fatima\u00a0I. Yasser Bassam\u00a0H. Abd and Saad Abbas. 2021. Detection of confusion behavior using a facial expression based on different classification algorithms. Engineering and Technology Journal 39 2 (A) (2021) 316\u2013325. 10.30684\/etj.v39i2A.1750","DOI":"10.30684\/etj.v39i2A.1750"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2819951"},{"key":"e_1_3_3_1_39_2","unstructured":"Gholamreza Zareian Seyyed Mohammad\u00a0Reza Adel and Fahimeh\u00a0Alizadeh Noghani. 2015. The effect of multimodal presentation on EFL learners\u2019 listening comprehension and self-efficacy. Academic Research International 6 1 (2015) 263."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Yueyuan Zheng Xinchen Ye and Janet\u00a0H. Hsiao. 2022. Does adding video and subtitles to an audio lesson facilitate its comprehension? Learning and Instruction 77 (2022) 101542. 10.1016\/j.learninstruc.2021.101542","DOI":"10.1016\/j.learninstruc.2021.101542"}],"event":{"name":"CSCW Companion '25: Companion of the Computer-Supported Cooperative Work and Social Computing","location":"Bergen Norway","acronym":"CSCW Companion '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Companion Publication of the 2025 Conference on Computer-Supported Cooperative Work and Social Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715070.3749225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:45:50Z","timestamp":1767980750000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715070.3749225"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":39,"alternative-id":["10.1145\/3715070.3749225","10.1145\/3715070"],"URL":"https:\/\/doi.org\/10.1145\/3715070.3749225","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}