{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T23:02:48Z","timestamp":1781218968629,"version":"3.54.1"},"reference-count":35,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T00:00:00Z","timestamp":1624924800000},"content-version":"vor","delay-in-days":28,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004807","name":"California Department of Fish and Game","doi-asserted-by":"publisher","award":["376714276"],"award-info":[{"award-number":["376714276"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"California Department of Fish and Game","doi-asserted-by":"publisher","award":["455910360"],"award-info":[{"award-number":["455910360"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Mixed\u2010initiative visual analytics systems support collaborative human\u2010machine decision\u2010making processes. However, many multi\u2010objective optimization tasks, such as topic model refinement, are highly subjective and context\u2010dependent. Hence, systems need to adapt their optimization suggestions throughout the interactive refinement process to provide efficient guidance. To tackle this challenge, we present a technique for learning context\u2010dependent user preferences and demonstrate its applicability to topic model refinement. We deploy agents with distinct associated optimization strategies that compete for the user's acceptance of their suggestions. To decide when to provide guidance, each agent maintains an intelligible, rule\u2010based classifier over context vectorizations that captures the development of quality metrics between distinct analysis states. By observing implicit and explicit user feedback, agents learn in which contexts to provide their specific guidance operation. An agent in topic model refinement might, for example, learn to react to declining model coherence by suggesting to split a topic. Our results confirm that the rules learned by agents capture contextual user preferences. Further, we show that the learned rules are transferable between similar datasets, avoiding common cold\u2010start problems and enabling a continuous refinement of agents across corpora.<\/jats:p>","DOI":"10.1111\/cgf.14301","type":"journal-article","created":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T16:48:33Z","timestamp":1624985313000},"page":"215-226","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Learning Contextualized User Preferences for Co\u2010Adaptive Guidance in Mixed\u2010Initiative Topic Model Refinement"],"prefix":"10.1111","volume":"40","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-2416-8639","authenticated-orcid":false,"given":"F.","family":"Sperrle","sequence":"first","affiliation":[{"name":"University of Konstanz"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-6840-5341","authenticated-orcid":false,"given":"H.","family":"Sch\u00e4fer","sequence":"additional","affiliation":[{"name":"University of Konstanz"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D.","family":"Keim","sequence":"additional","affiliation":[{"name":"University of Konstanz"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-8526-2613","authenticated-orcid":false,"given":"M.","family":"El\u2010Assady","sequence":"additional","affiliation":[{"name":"University of Konstanz"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,6,29]]},"reference":[{"key":"e_1_2_11_2_2","doi-asserted-by":"crossref","unstructured":"AndrienkoG. AndrienkoN. RinzivilloS. NanniM. PedreschiD. GiannottiF.: Interactive visual clustering of large collections of trajectories. InIEEE Symposium on Visual Analytics Science and Technology(2009) pp.3\u201310. doi:10.1109\/VAST.2009.5332584. 2","DOI":"10.1109\/VAST.2009.5332584"},{"key":"e_1_2_11_3_2","doi-asserted-by":"crossref","unstructured":"AnkerstM. EsterM. KriegelH.\u2010P.: Towards an effective cooperation of the user and the computer for classification. InProc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining(2000) pp.179\u2013188. doi:10.1145\/347090.347124. 2","DOI":"10.1145\/347090.347124"},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/5254.796083"},{"key":"e_1_2_11_5_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467\u20108659.2011.01938.x"},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4\u20105.993"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2018.09.003"},{"key":"e_1_2_11_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2598468"},{"key":"e_1_2_11_9_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13730"},{"key":"e_1_2_11_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.212"},{"key":"e_1_2_11_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.09.013"},{"key":"e_1_2_11_12_2","unstructured":"CNN Political Unit:Transcript: First presidential debate.https:\/\/2.zoppoz.workers.dev:443\/https\/edition.cnn.com\/2012\/10\/03\/politics\/debate-transcript\/index.html. 8 9"},{"key":"e_1_2_11_13_2","unstructured":"CNN Political Unit:Transcript: Second presidential debate.https:\/\/2.zoppoz.workers.dev:443\/http\/politicalticker.blogs.cnn.com\/2012\/10\/16\/transcript-second-presidential-debate\/. 8 9"},{"key":"e_1_2_11_14_2","doi-asserted-by":"crossref","unstructured":"DruckerS. M. FisherD. BasuS.: Helping Users Sort Faster with Adaptive Machine Learning Recommendations. InHuman\u2010Computer Interaction \u2013 INTERACT(2011) Campos P. Graham N. Jorge J. Nunes N. Palanque P. Winckler M. (Eds.) pp.187\u2013203. 2","DOI":"10.1007\/978-3-642-23765-2_13"},{"issue":"1","key":"e_1_2_11_15_2","first-page":"61","article-title":"Accurate Methods for the Statistics of Surprise and Coincidence","volume":"19","author":"Dunning T.","year":"1993","journal-title":"Computational Linguistics"},{"key":"e_1_2_11_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.162"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934654"},{"key":"e_1_2_11_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864769"},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2745080"},{"key":"e_1_2_11_20_2","doi-asserted-by":"crossref","unstructured":"EndertA. FiauxP. NorthC.: Semantic Interaction for Visual Text Analytics. InProc. Conf. Human Factors in Computing Systems(2012) pp.473\u2013482. doi:10.1145\/2207676.2207741. 2","DOI":"10.1145\/2207676.2207741"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994\u2010013\u20105413\u20100"},{"key":"e_1_2_11_22_2","doi-asserted-by":"crossref","unstructured":"HoqueE. CareniniG.: ConVisIT: Interactive Topic Modeling for Exploring Asynchronous Online Conversations. InProc. Int. Conf. Intelligent User Interfaces(2015) pp.169\u2013180. doi:10.1145\/2678025.2701370. 2","DOI":"10.1145\/2678025.2701370"},{"key":"e_1_2_11_23_2","doi-asserted-by":"crossref","unstructured":"HohmanF. SrinivasanA. DruckerS. M.: TeleGam: Combining Visualization and Verbalization for Interpretable Machine Learning. InIEEE Visualization Conference (VIS Short)(2019) pp.151\u2013155. doi:10.1109\/VISUAL.2019.8933695. 5","DOI":"10.31219\/osf.io\/p3wnm"},{"key":"e_1_2_11_24_2","doi-asserted-by":"crossref","unstructured":"KimH. DrakeB. EndertA. ParkH.: ArchiText: Interactive Hierarchical Topic Modeling.IEEE Trans. Visualization and Computer Graphics(2020) 1\u201312. doi:10.1109\/TVCG.2020.2981456. 2","DOI":"10.1109\/TVCG.2020.2981456"},{"key":"e_1_2_11_25_2","doi-asserted-by":"crossref","unstructured":"KaastraL. T. FisherB.: Field Experiment Methodology for Pair Analytics. InProc. Workshop on Beyond Time and Errors: Novel Evaluation Methods for Visualization at VIS(2014) pp.152\u2013159. doi:10.1145\/2669557.2669572. 7","DOI":"10.1145\/2669557.2669572"},{"key":"e_1_2_11_26_2","doi-asserted-by":"crossref","unstructured":"KochJ. LuceroA. HegemannL. OulasvirtaA.: May AI?: Design Ideation with Cooperative Contextual Bandits. InProc. CHI Conf. Human Factors in Computing Systems(2019) pp.1\u201312. doi:10.1145\/3290605.3300863. 2","DOI":"10.1145\/3290605.3300863"},{"key":"e_1_2_11_27_2","unstructured":"LangK.:Home Page for 20 Newsgroups Data Set.https:\/\/2.zoppoz.workers.dev:443\/http\/qwone.com\/jason\/20Newsgroups\/. 6"},{"key":"e_1_2_11_28_2","unstructured":"McDaidA. F. GreeneD. HurleyN.: Normalized Mutual Information to evaluate overlapping community finding algorithms.arXiv e\u2010prints(2013) 1\u20133. arXiv:1110.2515. 6"},{"key":"e_1_2_11_29_2","unstructured":"McInnesL. HealyJ. MelvilleJ.: UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.arXiv e\u2010prints(2018) 1\u201363. arXiv:1802.03426. 4"},{"key":"e_1_2_11_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744478"},{"key":"e_1_2_11_31_2","unstructured":"SevastjanovaR. BeckF. EllB. TurkayC. HenkinR. ButtM. KeimD. A. El\u2010AssadyM.: Going beyond Visualization : Verbalization as Complementary Medium to Explain Machine Learning Models. InWorkshop on Visualization for AI Explainability at IEEE VIS(2018) pp.1\u20136. 5"},{"key":"e_1_2_11_32_2","unstructured":"SanhV. DebutL. ChaumondJ. WolfT.: DistilBERT a distilled version of BERT: smaller faster cheaper and lighter.arXiv e\u2010prints(2020) 1\u20135. arXiv:1910.01108. 4"},{"key":"e_1_2_11_33_2","unstructured":"SperrleF. JeitlerA. BernardJ. KeimD. El\u2010AssadyM.: Learning and Teaching in Co\u2010Adaptive Guidancefor Mixed\u2010Initiative Visual Analytics.EuroVis Workshop on Visual Analytics(2020) 1\u20135. doi:10.2312\/eurova.20201088. 1 2 3"},{"key":"e_1_2_11_34_2","doi-asserted-by":"crossref","unstructured":"SperrleF. SevastjanovaR. KehlbeckR. El\u2010AssadyM.: VIANA: Visual Interactive Annotation of Argumentation. InProc. IEEE Conf. Visual Analytics Science and Technology (VAST)(2019) pp.1\u201312. doi:10.1109\/VAST47406.2019.8986917. 5","DOI":"10.1109\/VAST47406.2019.8986917"},{"key":"e_1_2_11_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2430837"},{"key":"e_1_2_11_36_2","doi-asserted-by":"crossref","unstructured":"ZakiM. J. HsiaoC.\u2010J.: CHARM: An Efficient Algorithm for Closed Itemset Mining. InProc. SIAM Int. Conf. on Data Mining(2002) pp.457\u2013473. doi:10.1137\/1.9781611972726.27. 6","DOI":"10.1137\/1.9781611972726.27"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14301","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.14301","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T23:33:41Z","timestamp":1692833621000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.14301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":35,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["10.1111\/cgf.14301"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1111\/cgf.14301","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6]]},"assertion":[{"value":"2021-06-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}