{"data":{"id":"10.4121/86e41488-701f-4d8f-aae6-8d1d61e22e9b","type":"dois","attributes":{"doi":"10.4121/86e41488-701f-4d8f-aae6-8d1d61e22e9b","prefix":"10.4121","suffix":"86e41488-701f-4d8f-aae6-8d1d61e22e9b","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Verstegen Rutger","nameType":"Personal","givenName":"Rutger","familyName":"Verstegen","nameIdentifiers":[{"nameIdentifier":"0000-0003-1934-2898","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]},{"name":"Pavlo Bazilinskyy","nameType":"Personal","givenName":"Pavlo","familyName":"Bazilinskyy","nameIdentifiers":[{"nameIdentifier":"0000-0001-9565-8240","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]},{"name":"Marieke Martens","nameType":"Personal","givenName":"Marieke","familyName":"Martens","nameIdentifiers":[{"nameIdentifier":"0000-0002-1661-7019","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]}],"titles":[{"title":"Supplementary material for the paper: \"Exploring LLM-Based Fragment Selection in Video Ethnography of Interactions between Automated Vehicles and Other Road Users\""}],"publisher":"4TU.ResearchData","container":{},"publicationYear":2026,"subjects":[{"subject":"Ground Transport","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"8801"},{"subject":"Transport","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"88"},{"subject":"Automated Vehicles"},{"subject":"Ethnography"},{"subject":"Large Language Models (LLMs)"},{"subject":"Video analysis"},{"subject":"Vehicle interaction"}],"contributors":[{"name":"TU Eindhoven, Department of Industrial Design, Computational Design Systems","nameType":"Organizational","contributorType":"Other","affiliation":[],"nameIdentifiers":[]}],"dates":[{"date":"2026-07-14","dateType":"Issued"}],"language":"en","types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"IsVersionOf","relatedIdentifier":"10.4121/86e41488-701f-4d8f-aae6-8d1d61e22e9b.v1","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[".txt"],"version":"1","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"Supplementary material for the paper: Rutger Verstegen, Pavlo Bazilinskyy and Marieke Martens. (2026). Exploring LLM-Based Fragment Selection in Video Ethnography of Interactions between Automated Vehicles and Other Road Users. HCII 2026 - Late Breaking Posters\u003cbr\u003eWith the increasing application of automated vehicles (AVs), publicly shared ride recordings are also growing, forming a valuable resource for online ethnography research. Qualitative content analysis by humans, however, is time-intensive and not well suited for large datasets. Therefore, this paper proposes the use of a multimodal large language model (LLM) for the selection of interaction fragments between AVs and other road users (ORUs), using the LLM to identify interaction segments for further human coding. Findings from an initial exploration using Gemini 2.5 Pro show that the model identified 4 out of 9 of the interaction fragments selected by human coders, while also struggling with hallucinations. By proposing the usage of multimodal LLMs for interaction fragment selection, and an exploration of this technique, this paper takes a first step toward more scalable digital video analysis of AV–ORU interactions.\u003cbr\u003eStructure:*/LLM-output.txt: Contains the full output from Gemini 2.5 Pro. \u003cbr\u003eNotes:LMM output was collected June 4th 2026.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[{"awardTitle":"NWO-NWA “Acting under uncertainty” (ACT) ","funderName":"NWO","awardNumber":"NWA.1292.19.298"}],"xml":"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","url":"https://data.4tu.nl/datasets/86e41488-701f-4d8f-aae6-8d1d61e22e9b","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-07-14T14:59:00.000Z","registered":"2026-07-14T14:59:01.000Z","published":"2026","updated":"2026-07-14T14:59:01.000Z"},"relationships":{"client":{"data":{"id":"delft.data4tu","type":"clients"}},"provider":{"data":{"id":"scpr","type":"providers"}},"media":{"data":{"id":"10.4121/86e41488-701f-4d8f-aae6-8d1d61e22e9b","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[{"id":"10.4121/86e41488-701f-4d8f-aae6-8d1d61e22e9b.v1","type":"dois"}]}}}}