Causal Perception in Question-Answering Systems
Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investiga...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2021-01 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Po-Ming Law Leo Yu-Ho Lo Endert, Alex Stasko, John Qu, Huamin |
description | Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investigate how such claims might mislead users, we conducted two crowdsourced experiments to study the impact of showing different information on user perceptions of a question-answering system. We found that in a system that occasionally provided unreasonable responses, showing a scatterplot increased the plausibility of unreasonable causal claims. Also, simply warning participants that correlation is not causation seemed to lead participants to accept reasonable causal claims more cautiously. We observed a strong tendency among participants to associate correlation with causation. Yet, the warning appeared to reduce the tendency. Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems. |
doi_str_mv | 10.48550/arxiv.2012.14477 |
format | Article |
fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2012_14477</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2474510160</sourcerecordid><originalsourceid>FETCH-LOGICAL-a520-fd499fb2afe61b0123867ddc92187a5c5830d6af3c6f4fb9b8803167bea138613</originalsourceid><addsrcrecordid>eNotj0tLw0AURgdBsNT-AFcGXCe9c-eZZQk-CgUVuw-TZEamtEmcadT-e5PW1b2Lw8c5hNxRyLgWApYm_PrvDIFiRjlX6orMkDGaao54QxYx7gAApUIh2IwsCzNEs0_ebKhtf_Rdm_g2eR9snP501cYfG3z7mXyc4tEe4i25dmYf7eL_zsn26XFbvKSb1-d1sdqkRiCkruF57io0zkpajSpMS9U0dY5UKyNqoRk00jhWS8ddlVdaA6NSVdbQEaVsTu4vs-easg_-YMKpnKrKc9VIPFyIPnRfk26564bQjk4lcsUFBSqB_QGZeU5-</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2474510160</pqid></control><display><type>article</type><title>Causal Perception in Question-Answering Systems</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Po-Ming Law ; Leo Yu-Ho Lo ; Endert, Alex ; Stasko, John ; Qu, Huamin</creator><creatorcontrib>Po-Ming Law ; Leo Yu-Ho Lo ; Endert, Alex ; Stasko, John ; Qu, Huamin</creatorcontrib><description>Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investigate how such claims might mislead users, we conducted two crowdsourced experiments to study the impact of showing different information on user perceptions of a question-answering system. We found that in a system that occasionally provided unreasonable responses, showing a scatterplot increased the plausibility of unreasonable causal claims. Also, simply warning participants that correlation is not causation seemed to lead participants to accept reasonable causal claims more cautiously. We observed a strong tendency among participants to associate correlation with causation. Yet, the warning appeared to reduce the tendency. Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2012.14477</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Causation ; Computer Science - Human-Computer Interaction ; Data analysis ; Questions ; Root cause analysis</subject><ispartof>arXiv.org, 2021-01</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,781,882,27906</link.rule.ids><backlink>$$Uhttps://doi.org/10.1145/3411764.3445444$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2012.14477$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Po-Ming Law</creatorcontrib><creatorcontrib>Leo Yu-Ho Lo</creatorcontrib><creatorcontrib>Endert, Alex</creatorcontrib><creatorcontrib>Stasko, John</creatorcontrib><creatorcontrib>Qu, Huamin</creatorcontrib><title>Causal Perception in Question-Answering Systems</title><title>arXiv.org</title><description>Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investigate how such claims might mislead users, we conducted two crowdsourced experiments to study the impact of showing different information on user perceptions of a question-answering system. We found that in a system that occasionally provided unreasonable responses, showing a scatterplot increased the plausibility of unreasonable causal claims. Also, simply warning participants that correlation is not causation seemed to lead participants to accept reasonable causal claims more cautiously. We observed a strong tendency among participants to associate correlation with causation. Yet, the warning appeared to reduce the tendency. Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems.</description><subject>Causation</subject><subject>Computer Science - Human-Computer Interaction</subject><subject>Data analysis</subject><subject>Questions</subject><subject>Root cause analysis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj0tLw0AURgdBsNT-AFcGXCe9c-eZZQk-CgUVuw-TZEamtEmcadT-e5PW1b2Lw8c5hNxRyLgWApYm_PrvDIFiRjlX6orMkDGaao54QxYx7gAApUIh2IwsCzNEs0_ebKhtf_Rdm_g2eR9snP501cYfG3z7mXyc4tEe4i25dmYf7eL_zsn26XFbvKSb1-d1sdqkRiCkruF57io0zkpajSpMS9U0dY5UKyNqoRk00jhWS8ddlVdaA6NSVdbQEaVsTu4vs-easg_-YMKpnKrKc9VIPFyIPnRfk26564bQjk4lcsUFBSqB_QGZeU5-</recordid><startdate>20210106</startdate><enddate>20210106</enddate><creator>Po-Ming Law</creator><creator>Leo Yu-Ho Lo</creator><creator>Endert, Alex</creator><creator>Stasko, John</creator><creator>Qu, Huamin</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210106</creationdate><title>Causal Perception in Question-Answering Systems</title><author>Po-Ming Law ; Leo Yu-Ho Lo ; Endert, Alex ; Stasko, John ; Qu, Huamin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a520-fd499fb2afe61b0123867ddc92187a5c5830d6af3c6f4fb9b8803167bea138613</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Causation</topic><topic>Computer Science - Human-Computer Interaction</topic><topic>Data analysis</topic><topic>Questions</topic><topic>Root cause analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Po-Ming Law</creatorcontrib><creatorcontrib>Leo Yu-Ho Lo</creatorcontrib><creatorcontrib>Endert, Alex</creatorcontrib><creatorcontrib>Stasko, John</creatorcontrib><creatorcontrib>Qu, Huamin</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Po-Ming Law</au><au>Leo Yu-Ho Lo</au><au>Endert, Alex</au><au>Stasko, John</au><au>Qu, Huamin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Causal Perception in Question-Answering Systems</atitle><jtitle>arXiv.org</jtitle><date>2021-01-06</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investigate how such claims might mislead users, we conducted two crowdsourced experiments to study the impact of showing different information on user perceptions of a question-answering system. We found that in a system that occasionally provided unreasonable responses, showing a scatterplot increased the plausibility of unreasonable causal claims. Also, simply warning participants that correlation is not causation seemed to lead participants to accept reasonable causal claims more cautiously. We observed a strong tendency among participants to associate correlation with causation. Yet, the warning appeared to reduce the tendency. Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2012.14477</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2021-01 |
issn | 2331-8422 |
language | eng |
recordid | cdi_arxiv_primary_2012_14477 |
source | arXiv.org; Free E- Journals |
subjects | Causation Computer Science - Human-Computer Interaction Data analysis Questions Root cause analysis |
title | Causal Perception in Question-Answering Systems |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T13%3A25%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Causal%20Perception%20in%20Question-Answering%20Systems&rft.jtitle=arXiv.org&rft.au=Po-Ming%20Law&rft.date=2021-01-06&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2012.14477&rft_dat=%3Cproquest_arxiv%3E2474510160%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2474510160&rft_id=info:pmid/&rfr_iscdi=true |