AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers Article Swipe

PDF

Alexander Wuttke , Matthias Aßenmacher , Christopher Klamm , Michael Lang , Quirin Würschinger , Frauke Kreuter ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2410.01824

Traditional methods for eliciting people's opinions face a trade-off between depth and scale: structured surveys enable large-scale data collection but limit respondents' ability to voice their opinions in their own words, while conversational interviews provide deeper insights but are resource-intensive. This study explores the potential of replacing human interviewers with large language models (LLMs) to conduct scalable conversational interviews. Our goal is to assess the performance of AI Conversational Interviewing and to identify opportunities for improvement in a controlled environment. We conducted a small-scale, in-depth study with university students who were randomly assigned to a conversational interview by either AI or human interviewers, both employing identical questionnaires on political topics. Various quantitative and qualitative measures assessed interviewer adherence to guidelines, response quality, participant engagement, and overall interview efficacy. The findings indicate the viability of AI Conversational Interviewing in producing quality data comparable to traditional methods, with the added benefit of scalability. We publish our data and materials for re-use and present specific recommendations for effective implementation.

Related Topics

Concepts

Interview Psychology Social psychology Computer science Applied psychology Political science Law

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2410.01824
PDF: https://arxiv.org/pdf/2410.01824
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4403853768

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4403853768

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2410.01824

Digital Object Identifier
Title: AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-09-16

Full publication date if available
Authors: Alexander Wuttke, Matthias Aßenmacher, Christopher Klamm, Michael Lang, Quirin Würschinger, Frauke Kreuter

List of authors in order
Landing page: https://arxiv.org/abs/2410.01824

Publisher landing page
PDF URL: https://arxiv.org/pdf/2410.01824

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2410.01824

Direct OA link when available
Concepts: Interview, Psychology, Social psychology, Computer science, Applied psychology, Political science, Law

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4403853768
doi	https://doi.org/10.48550/arxiv.2410.01824
ids.doi	https://doi.org/10.48550/arxiv.2410.01824
ids.openalex	https://openalex.org/W4403853768
fwci	0.24339971
type	preprint
title	AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11636
topics[0].field.id	https://openalex.org/fields/27
topics[0].field.display_name	Medicine
topics[0].score	0.9886999726295471
topics[0].domain.id	https://openalex.org/domains/4
topics[0].domain.display_name	Health Sciences
topics[0].subfield.id	https://openalex.org/subfields/2718
topics[0].subfield.display_name	Health Informatics
topics[0].display_name	Artificial Intelligence in Healthcare and Education
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C24845683
concepts[0].level	2
concepts[0].score	0.8703960180282593
concepts[0].wikidata	https://www.wikidata.org/wiki/Q178651
concepts[0].display_name	Interview
concepts[1].id	https://openalex.org/C15744967
concepts[1].level	0
concepts[1].score	0.4945795238018036
concepts[1].wikidata	https://www.wikidata.org/wiki/Q9418
concepts[1].display_name	Psychology
concepts[2].id	https://openalex.org/C77805123
concepts[2].level	1
concepts[2].score	0.38091322779655457
concepts[2].wikidata	https://www.wikidata.org/wiki/Q161272
concepts[2].display_name	Social psychology
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.33499598503112793
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C75630572
concepts[4].level	1
concepts[4].score	0.33264145255088806
concepts[4].wikidata	https://www.wikidata.org/wiki/Q538904
concepts[4].display_name	Applied psychology
concepts[5].id	https://openalex.org/C17744445
concepts[5].level	0
concepts[5].score	0.3160399794578552
concepts[5].wikidata	https://www.wikidata.org/wiki/Q36442
concepts[5].display_name	Political science
concepts[6].id	https://openalex.org/C199539241
concepts[6].level	1
concepts[6].score	0.0
concepts[6].wikidata	https://www.wikidata.org/wiki/Q7748
concepts[6].display_name	Law
keywords[0].id	https://openalex.org/keywords/interview
keywords[0].score	0.8703960180282593
keywords[0].display_name	Interview
keywords[1].id	https://openalex.org/keywords/psychology
keywords[1].score	0.4945795238018036
keywords[1].display_name	Psychology
keywords[2].id	https://openalex.org/keywords/social-psychology
keywords[2].score	0.38091322779655457
keywords[2].display_name	Social psychology
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.33499598503112793
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/applied-psychology
keywords[4].score	0.33264145255088806
keywords[4].display_name	Applied psychology
keywords[5].id	https://openalex.org/keywords/political-science
keywords[5].score	0.3160399794578552
keywords[5].display_name	Political science
language	en
locations[0].id	pmh:oai:arXiv.org:2410.01824
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2410.01824
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2410.01824
locations[1].id	doi:10.48550/arxiv.2410.01824
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article-journal
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2410.01824
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5004036470
authorships[0].author.orcid	https://orcid.org/0000-0002-9579-5357
authorships[0].author.display_name	Alexander Wuttke
authorships[0].author_position	first
authorships[0].raw_author_name	Wuttke, Alexander
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5114439647
authorships[1].author.orcid
authorships[1].author.display_name	Matthias Aßenmacher
authorships[1].author_position	middle
authorships[1].raw_author_name	Aßenmacher, Matthias
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5114439648
authorships[2].author.orcid
authorships[2].author.display_name	Christopher Klamm
authorships[2].author_position	middle
authorships[2].raw_author_name	Klamm, Christopher
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5011132491
authorships[3].author.orcid	https://orcid.org/0000-0003-2466-2589
authorships[3].author.display_name	Michael Lang
authorships[3].author_position	middle
authorships[3].raw_author_name	Lang, Max M.
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5114439649
authorships[4].author.orcid
authorships[4].author.display_name	Quirin Würschinger
authorships[4].author_position	middle
authorships[4].raw_author_name	Würschinger, Quirin
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5038390320
authorships[5].author.orcid	https://orcid.org/0000-0002-7339-2645
authorships[5].author.display_name	Frauke Kreuter
authorships[5].author_position	last
authorships[5].raw_author_name	Kreuter, Frauke
authorships[5].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2410.01824
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11636
primary_topic.field.id	https://openalex.org/fields/27
primary_topic.field.display_name	Medicine
primary_topic.score	0.9886999726295471
primary_topic.domain.id	https://openalex.org/domains/4
primary_topic.domain.display_name	Health Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2718
primary_topic.subfield.display_name	Health Informatics
primary_topic.display_name	Artificial Intelligence in Healthcare and Education
related_works	https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W4391375266, https://openalex.org/W4235390613, https://openalex.org/W2010073985, https://openalex.org/W2005156726, https://openalex.org/W1979650037, https://openalex.org/W1930429402, https://openalex.org/W2461828801, https://openalex.org/W2064700171
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2410.01824
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2410.01824
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2410.01824
primary_location.id	pmh:oai:arXiv.org:2410.01824
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2410.01824
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2410.01824
publication_date	2024-09-16
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	7, 77, 82, 94
abstract_inverted_index.AI	67, 99, 134
abstract_inverted_index.We	80, 151
abstract_inverted_index.by	97
abstract_inverted_index.in	27, 76, 137
abstract_inverted_index.is	61
abstract_inverted_index.of	45, 66, 133, 149
abstract_inverted_index.on	107
abstract_inverted_index.or	100
abstract_inverted_index.to	23, 54, 62, 71, 93, 118, 142
abstract_inverted_index.Our	59
abstract_inverted_index.The	128
abstract_inverted_index.and	11, 70, 112, 124, 155, 159
abstract_inverted_index.are	38
abstract_inverted_index.but	19, 37
abstract_inverted_index.for	2, 74, 157, 163
abstract_inverted_index.our	153
abstract_inverted_index.own	29
abstract_inverted_index.the	43, 64, 131, 146
abstract_inverted_index.who	89
abstract_inverted_index.This	40
abstract_inverted_index.both	103
abstract_inverted_index.data	17, 140, 154
abstract_inverted_index.face	6
abstract_inverted_index.goal	60
abstract_inverted_index.were	90
abstract_inverted_index.with	49, 86, 145
abstract_inverted_index.added	147
abstract_inverted_index.depth	10
abstract_inverted_index.human	47, 101
abstract_inverted_index.large	50
abstract_inverted_index.limit	20
abstract_inverted_index.study	41, 85
abstract_inverted_index.their	25, 28
abstract_inverted_index.voice	24
abstract_inverted_index.while	31
abstract_inverted_index.(LLMs)	53
abstract_inverted_index.assess	63
abstract_inverted_index.deeper	35
abstract_inverted_index.either	98
abstract_inverted_index.enable	15
abstract_inverted_index.models	52
abstract_inverted_index.re-use	158
abstract_inverted_index.scale:	12
abstract_inverted_index.words,	30
abstract_inverted_index.Various	110
abstract_inverted_index.ability	22
abstract_inverted_index.benefit	148
abstract_inverted_index.between	9
abstract_inverted_index.conduct	55
abstract_inverted_index.methods	1
abstract_inverted_index.overall	125
abstract_inverted_index.present	160
abstract_inverted_index.provide	34
abstract_inverted_index.publish	152
abstract_inverted_index.quality	139
abstract_inverted_index.surveys	14
abstract_inverted_index.topics.	109
abstract_inverted_index.assessed	115
abstract_inverted_index.assigned	92
abstract_inverted_index.explores	42
abstract_inverted_index.findings	129
abstract_inverted_index.identify	72
abstract_inverted_index.in-depth	84
abstract_inverted_index.indicate	130
abstract_inverted_index.insights	36
abstract_inverted_index.language	51
abstract_inverted_index.measures	114
abstract_inverted_index.methods,	144
abstract_inverted_index.opinions	5, 26
abstract_inverted_index.people's	4
abstract_inverted_index.quality,	121
abstract_inverted_index.randomly	91
abstract_inverted_index.response	120
abstract_inverted_index.scalable	56
abstract_inverted_index.specific	161
abstract_inverted_index.students	88
abstract_inverted_index.adherence	117
abstract_inverted_index.conducted	81
abstract_inverted_index.effective	164
abstract_inverted_index.efficacy.	127
abstract_inverted_index.eliciting	3
abstract_inverted_index.employing	104
abstract_inverted_index.identical	105
abstract_inverted_index.interview	96, 126
abstract_inverted_index.materials	156
abstract_inverted_index.political	108
abstract_inverted_index.potential	44
abstract_inverted_index.producing	138
abstract_inverted_index.replacing	46
abstract_inverted_index.trade-off	8
abstract_inverted_index.viability	132
abstract_inverted_index.collection	18
abstract_inverted_index.comparable	141
abstract_inverted_index.controlled	78
abstract_inverted_index.interviews	33
abstract_inverted_index.structured	13
abstract_inverted_index.university	87
abstract_inverted_index.Traditional	0
abstract_inverted_index.engagement,	123
abstract_inverted_index.guidelines,	119
abstract_inverted_index.improvement	75
abstract_inverted_index.interviewer	116
abstract_inverted_index.interviews.	58
abstract_inverted_index.large-scale	16
abstract_inverted_index.participant	122
abstract_inverted_index.performance	65
abstract_inverted_index.qualitative	113
abstract_inverted_index.traditional	143
abstract_inverted_index.Interviewing	69, 136
abstract_inverted_index.environment.	79
abstract_inverted_index.interviewers	48
abstract_inverted_index.quantitative	111
abstract_inverted_index.respondents'	21
abstract_inverted_index.scalability.	150
abstract_inverted_index.small-scale,	83
abstract_inverted_index.interviewers,	102
abstract_inverted_index.opportunities	73
abstract_inverted_index.Conversational	68, 135
abstract_inverted_index.conversational	32, 57, 95
abstract_inverted_index.questionnaires	106
abstract_inverted_index.implementation.	165
abstract_inverted_index.recommendations	162
abstract_inverted_index.resource-intensive.	39
cited_by_percentile_year.max	95
cited_by_percentile_year.min	91
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile.value	0.53535354
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False