Mapping the Design Space of Human-AI Interaction in Text Summarization

Mapping the Design Space of Human-AI Interaction in Text Summarization

Automatic text summarization systems commonly involve humans for preparing data or evaluating model performance, yet, there lacks a systematic understanding of humans' roles, experience, and needs when interacting with or being assisted by AI. From a human-centered perspective, we map the desig...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cheng, Ruijia, Smith-Renner, Alison, Zhang, Ke, Tetreault, Joel R, Jaimes, Alejandro
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Human-Computer Interaction
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Cheng, Ruijia
Smith-Renner, Alison
Zhang, Ke
Tetreault, Joel R
Jaimes, Alejandro
description Automatic text summarization systems commonly involve humans for preparing data or evaluating model performance, yet, there lacks a systematic understanding of humans' roles, experience, and needs when interacting with or being assisted by AI. From a human-centered perspective, we map the design opportunities and considerations for human-AI interaction in text summarization and broader text generation tasks. We first conducted a systematic literature review of 70 papers, developing a taxonomy of five interactions in AI-assisted text generation and relevant design dimensions. We designed text summarization prototypes for each interaction. We then interviewed 16 users, aided by the prototypes, to understand their expectations, experience, and needs regarding efficiency, control, and trust with AI in text summarization and propose design considerations accordingly.
doi_str_mv 10.48550/arxiv.2206.14863
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2206_14863</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2206_14863</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-ed103e03ed9378f64f4a0df3e083fcc500eeaab544ef5674110ec94409ae10b83</originalsourceid><addsrcrecordid>eNotj8FOwzAQRH3hgAofwAn_QMK6XjvOsSqURiri0NyjrbMulogbpSkqfD1pQRpppHcYzRPiQUGOzhh4ouEcv_L5HGyu0Fl9K1Zv1Pcx7eX4wfKZj3Gf5LYnz_IQ5PrUUcoWlazSyAP5MR6SjEnWfB7l9tR1NMQfutA7cRPo88j3_z0T9eqlXq6zzftrtVxsMrKFzrhVoHlKW-rCBYsBCdowIaeD9waAmWhnEDkYW6BSwL5EhJJYwc7pmXj8m72KNP0QpwvfzUWouQrpX4n3RYQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Mapping the Design Space of Human-AI Interaction in Text Summarization</title><source>arXiv.org</source><creator>Cheng, Ruijia ; Smith-Renner, Alison ; Zhang, Ke ; Tetreault, Joel R ; Jaimes, Alejandro</creator><creatorcontrib>Cheng, Ruijia ; Smith-Renner, Alison ; Zhang, Ke ; Tetreault, Joel R ; Jaimes, Alejandro</creatorcontrib><description>Automatic text summarization systems commonly involve humans for preparing data or evaluating model performance, yet, there lacks a systematic understanding of humans' roles, experience, and needs when interacting with or being assisted by AI. From a human-centered perspective, we map the design opportunities and considerations for human-AI interaction in text summarization and broader text generation tasks. We first conducted a systematic literature review of 70 papers, developing a taxonomy of five interactions in AI-assisted text generation and relevant design dimensions. We designed text summarization prototypes for each interaction. We then interviewed 16 users, aided by the prototypes, to understand their expectations, experience, and needs regarding efficiency, control, and trust with AI in text summarization and propose design considerations accordingly.</description><identifier>DOI: 10.48550/arxiv.2206.14863</identifier><language>eng</language><subject>Computer Science - Human-Computer Interaction</subject><creationdate>2022-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2206.14863$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2206.14863$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Cheng, Ruijia</creatorcontrib><creatorcontrib>Smith-Renner, Alison</creatorcontrib><creatorcontrib>Zhang, Ke</creatorcontrib><creatorcontrib>Tetreault, Joel R</creatorcontrib><creatorcontrib>Jaimes, Alejandro</creatorcontrib><title>Mapping the Design Space of Human-AI Interaction in Text Summarization</title><description>Automatic text summarization systems commonly involve humans for preparing data or evaluating model performance, yet, there lacks a systematic understanding of humans' roles, experience, and needs when interacting with or being assisted by AI. From a human-centered perspective, we map the design opportunities and considerations for human-AI interaction in text summarization and broader text generation tasks. We first conducted a systematic literature review of 70 papers, developing a taxonomy of five interactions in AI-assisted text generation and relevant design dimensions. We designed text summarization prototypes for each interaction. We then interviewed 16 users, aided by the prototypes, to understand their expectations, experience, and needs regarding efficiency, control, and trust with AI in text summarization and propose design considerations accordingly.</description><subject>Computer Science - Human-Computer Interaction</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8FOwzAQRH3hgAofwAn_QMK6XjvOsSqURiri0NyjrbMulogbpSkqfD1pQRpppHcYzRPiQUGOzhh4ouEcv_L5HGyu0Fl9K1Zv1Pcx7eX4wfKZj3Gf5LYnz_IQ5PrUUcoWlazSyAP5MR6SjEnWfB7l9tR1NMQfutA7cRPo88j3_z0T9eqlXq6zzftrtVxsMrKFzrhVoHlKW-rCBYsBCdowIaeD9waAmWhnEDkYW6BSwL5EhJJYwc7pmXj8m72KNP0QpwvfzUWouQrpX4n3RYQ</recordid><startdate>20220629</startdate><enddate>20220629</enddate><creator>Cheng, Ruijia</creator><creator>Smith-Renner, Alison</creator><creator>Zhang, Ke</creator><creator>Tetreault, Joel R</creator><creator>Jaimes, Alejandro</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220629</creationdate><title>Mapping the Design Space of Human-AI Interaction in Text Summarization</title><author>Cheng, Ruijia ; Smith-Renner, Alison ; Zhang, Ke ; Tetreault, Joel R ; Jaimes, Alejandro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-ed103e03ed9378f64f4a0df3e083fcc500eeaab544ef5674110ec94409ae10b83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Human-Computer Interaction</topic><toplevel>online_resources</toplevel><creatorcontrib>Cheng, Ruijia</creatorcontrib><creatorcontrib>Smith-Renner, Alison</creatorcontrib><creatorcontrib>Zhang, Ke</creatorcontrib><creatorcontrib>Tetreault, Joel R</creatorcontrib><creatorcontrib>Jaimes, Alejandro</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cheng, Ruijia</au><au>Smith-Renner, Alison</au><au>Zhang, Ke</au><au>Tetreault, Joel R</au><au>Jaimes, Alejandro</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Mapping the Design Space of Human-AI Interaction in Text Summarization</atitle><date>2022-06-29</date><risdate>2022</risdate><abstract>Automatic text summarization systems commonly involve humans for preparing data or evaluating model performance, yet, there lacks a systematic understanding of humans' roles, experience, and needs when interacting with or being assisted by AI. From a human-centered perspective, we map the design opportunities and considerations for human-AI interaction in text summarization and broader text generation tasks. We first conducted a systematic literature review of 70 papers, developing a taxonomy of five interactions in AI-assisted text generation and relevant design dimensions. We designed text summarization prototypes for each interaction. We then interviewed 16 users, aided by the prototypes, to understand their expectations, experience, and needs regarding efficiency, control, and trust with AI in text summarization and propose design considerations accordingly.</abstract><doi>10.48550/arxiv.2206.14863</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2206.14863
ispartof
issn
language eng
recordid cdi_arxiv_primary_2206_14863
source arXiv.org
subjects Computer Science - Human-Computer Interaction
title Mapping the Design Space of Human-AI Interaction in Text Summarization
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T12%3A24%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Mapping%20the%20Design%20Space%20of%20Human-AI%20Interaction%20in%20Text%20Summarization&rft.au=Cheng,%20Ruijia&rft.date=2022-06-29&rft_id=info:doi/10.48550/arxiv.2206.14863&rft_dat=%3Carxiv_GOX%3E2206_14863%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true