{"id":"https://openalex.org/W7164975232","doi":null,"title":"Towards Interpretable Neural Network-Based Sentiment Analysis Models: A Bottleneck-Based Latent Dimension Analysis","display_name":"Towards Interpretable Neural Network-Based Sentiment Analysis Models: A Bottleneck-Based Latent Dimension Analysis","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7164975232"},"language":"en","primary_location":{"id":"pmh:oai:minds.wisconsin.edu:1793/97632","doi":null,"is_oa":true,"landing_page_url":"http://digital.library.wisc.edu/1793/97632","pdf_url":"https://minds.wisconsin.edu/bitstream/1793/97632/1/Luo_uwm_0263D_14257.pdf","source":{"id":"https://openalex.org/S4306401622","display_name":"Minds at UW (University of Wisconsin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I135310074","host_organization_name":"University of Wisconsin\u2013Madison","host_organization_lineage":["https://openalex.org/I135310074"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dissertation"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://minds.wisconsin.edu/bitstream/1793/97632/1/Luo_uwm_0263D_14257.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066856675","display_name":"Manman Luo","orcid":"https://orcid.org/0000-0002-6644-9295","observed_orcids":["https://orcid.org/0000-0002-6644-9295"]},"institutions":[{"id":"https://openalex.org/I43579087","display_name":"University of Wisconsin\u2013Milwaukee","ror":"https://ror.org/031q21x57","country_code":"US","type":"education","lineage":["https://openalex.org/I43579087"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luo, Manman","raw_affiliation_strings":["Wisconsin-Milwaukee , 2026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin-Milwaukee , 2026","institution_ids":["https://openalex.org/I43579087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066856675"],"corresponding_institution_ids":["https://openalex.org/I43579087"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"sentiment analysis","score":0.7390000224113464},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.7680000066757202},{"id":"https://openalex.org/keywords/bottleneck-layer","display_name":"bottleneck layer","score":0.6349999904632568},{"id":"https://openalex.org/keywords/latent-dimensions","display_name":"latent dimensions","score":0.7210000157356262},{"id":"https://openalex.org/keywords/neural-network-interpretability","display_name":"neural network interpretability","score":0.5960000157356262},{"id":"https://openalex.org/keywords/linguistic-patterns","display_name":"linguistic patterns","score":0.5699999928474426},{"id":"https://openalex.org/keywords/discourse-structure","display_name":"discourse structure","score":0.7760000228881836},{"id":"https://openalex.org/keywords/complaint-discourse","display_name":"complaint discourse","score":0.42800000309944153},{"id":"https://openalex.org/keywords/narrative-style","display_name":"narrative style","score":0.7260000109672546},{"id":"https://openalex.org/keywords/stylistic-variation","display_name":"stylistic variation","score":0.746999979019165},{"id":"https://openalex.org/keywords/dimension-independence","display_name":"dimension independence","score":0.4790000021457672},{"id":"https://openalex.org/keywords/model-architecture-design","display_name":"model architecture design","score":0.4440000057220459},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.5419999957084656},{"id":"https://openalex.org/keywords/black-box-modeling","display_name":"black-box models","score":0.5139999985694885},{"id":"https://openalex.org/keywords/contribution-analysis","display_name":"contribution analysis","score":0.5099999904632568},{"id":"https://openalex.org/keywords/correlation-analysis","display_name":"correlation analysis","score":0.8169999718666077},{"id":"https://openalex.org/keywords/first-person-pronouns","display_name":"first-person pronouns","score":0.6779999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6685000061988831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6660000085830688},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6639999747276306},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.6438999772071838},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.6164000034332275},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47769999504089355},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.40529999136924744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39989998936653137},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:minds.wisconsin.edu:1793/97632","doi":null,"is_oa":true,"landing_page_url":"http://digital.library.wisc.edu/1793/97632","pdf_url":"https://minds.wisconsin.edu/bitstream/1793/97632/1/Luo_uwm_0263D_14257.pdf","source":{"id":"https://openalex.org/S4306401622","display_name":"Minds at UW (University of Wisconsin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I135310074","host_organization_name":"University of Wisconsin\u2013Madison","host_organization_lineage":["https://openalex.org/I135310074"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dissertation"}],"best_oa_location":{"id":"pmh:oai:minds.wisconsin.edu:1793/97632","doi":null,"is_oa":true,"landing_page_url":"http://digital.library.wisc.edu/1793/97632","pdf_url":"https://minds.wisconsin.edu/bitstream/1793/97632/1/Luo_uwm_0263D_14257.pdf","source":{"id":"https://openalex.org/S4306401622","display_name":"Minds at UW (University of Wisconsin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I135310074","host_organization_name":"University of Wisconsin\u2013Madison","host_organization_lineage":["https://openalex.org/I135310074"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dissertation"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164975232.pdf","grobid_xml":"https://content.openalex.org/works/W7164975232.grobid-xml"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1961993270","https://openalex.org/W1972145547","https://openalex.org/W1987425720","https://openalex.org/W1992892670","https://openalex.org/W1995561053","https://openalex.org/W2007257789","https://openalex.org/W2009055572","https://openalex.org/W2014902591","https://openalex.org/W2025899713","https://openalex.org/W2037452669","https://openalex.org/W2045738181","https://openalex.org/W2062913298","https://openalex.org/W2064230935","https://openalex.org/W2064351911","https://openalex.org/W2081375810","https://openalex.org/W2084046180","https://openalex.org/W2087850284","https://openalex.org/W2109872889","https://openalex.org/W2114068176","https://openalex.org/W2115792525","https://openalex.org/W2146111747","https://openalex.org/W2148034183","https://openalex.org/W2148506018","https://openalex.org/W2156413587","https://openalex.org/W2160660844","https://openalex.org/W2166706824","https://openalex.org/W2167049905","https://openalex.org/W2223340824","https://openalex.org/W2250539671","https://openalex.org/W2251124635","https://openalex.org/W2251648804","https://openalex.org/W2253519362","https://openalex.org/W2325658410","https://openalex.org/W2514299353","https://openalex.org/W2516915205","https://openalex.org/W2562231314","https://openalex.org/W2571253853","https://openalex.org/W2730000420","https://openalex.org/W2769632649","https://openalex.org/W2771344634","https://openalex.org/W2792670840","https://openalex.org/W2882319491","https://openalex.org/W2889996681","https://openalex.org/W2901478173","https://openalex.org/W2910215611","https://openalex.org/W2919704260","https://openalex.org/W2949998441","https://openalex.org/W2968210605","https://openalex.org/W3003681195","https://openalex.org/W3034317390","https://openalex.org/W3107577028","https://openalex.org/W3130339898","https://openalex.org/W3141714916","https://openalex.org/W3152486312","https://openalex.org/W3184119271","https://openalex.org/W3211111532","https://openalex.org/W4210658679","https://openalex.org/W4213072767","https://openalex.org/W4221150629","https://openalex.org/W4224917440","https://openalex.org/W4283794158","https://openalex.org/W4306317657","https://openalex.org/W4311477875","https://openalex.org/W4311640012","https://openalex.org/W4312084235","https://openalex.org/W4384519344","https://openalex.org/W4386860850","https://openalex.org/W4390591112","https://openalex.org/W4390715985","https://openalex.org/W4391344488","https://openalex.org/W4393684362","https://openalex.org/W4395065622","https://openalex.org/W4396760009","https://openalex.org/W4400017403","https://openalex.org/W4401394355","https://openalex.org/W4403172203","https://openalex.org/W4403437401","https://openalex.org/W4406800785","https://openalex.org/W4406949968","https://openalex.org/W4407160918","https://openalex.org/W4408953848","https://openalex.org/W4408979965","https://openalex.org/W4410315627","https://openalex.org/W4411456560","https://openalex.org/W4412642654","https://openalex.org/W4412673510","https://openalex.org/W4413387924","https://openalex.org/W4414669842","https://openalex.org/W4415025396","https://openalex.org/W4416765081","https://openalex.org/W4417136971","https://openalex.org/W7118579318","https://openalex.org/W7133201337"],"related_works":["https://openalex.org/W3028222879","https://openalex.org/W3004045412","https://openalex.org/W4415025396","https://openalex.org/W7131880024","https://openalex.org/W3013110756","https://openalex.org/W4390611570","https://openalex.org/W4321065579","https://openalex.org/W4304820937","https://openalex.org/W2976862955","https://openalex.org/W4406063152"],"abstract_inverted_index":{"Neural":[0],"network-based":[1,85,99,468],"models,":[2],"particularly":[3],"those":[4],"built":[5],"on":[6,48,164,185,438,445],"deep":[7,26,502],"learning":[8,503],"architectures,":[9],"have":[10],"achieved":[11],"superior":[12],"performance":[13,156,189],"in":[14,318,368,423,480],"sentiment":[15,21,61,86,100,257,282,433,441,469],"analysis":[16,22,87,127,384,470],"tasks":[17,498],"compared":[18,169],"with":[19,103,144,170,197,250,287,334,359,390,401],"traditional":[20],"approaches.":[23],"However,":[24],"the":[25,65,109,152,171,178,186,208,246,261,319,331,379,396,408,473,481],"learning-based":[27],"models":[28,88,471,504],"function":[29,277],"as":[30,278,304],"black":[31],"boxes,":[32],"making":[33],"it":[34],"difficult":[35],"to":[36,58,82,150,234,240,244,348,413,485,494,499],"understand":[37],"how":[38,60,129,236,309,446,501],"semantic":[39],"meaning":[40],"is":[41,62,132,162,201,214,311,345,399,411,448,483],"internally":[42,505],"represented.While":[43],"prior":[44],"work":[45],"has":[46,55,330],"focused":[47],"feature-level":[49],"or":[50,440],"attention-based":[51],"explanations,":[52],"less":[53],"attention":[54],"been":[56],"given":[57],"understanding":[59],"represented":[63],"within":[64],"internal":[66],"latent":[67,123,193,199,265],"space":[68],"of":[69,122,128,138,188,227,263,275,281],"these":[70],"models.":[71],"This":[72,113,452],"dissertation":[73],"addresses":[74],"this":[75],"gap":[76],"by":[77],"proposing":[78],"a":[79,90,97,104,119,195,463],"representation-level":[80],"approach":[81],"interpreting":[83],"neural":[84,98,467],"using":[89],"bottleneck":[91,105,146,321],"layer":[92,106],"architecture.":[93],"The":[94,160,174,253,383,476],"study":[95,453,482],"introduces":[96],"classification":[101,111,497],"model":[102,161,180,241,335,380],"placed":[107],"before":[108],"final":[110],"layer.":[112],"design":[114,457],"constrains":[115],"high-dimensional":[116],"representations":[117],"into":[118],"small":[120,273],"set":[121],"dimensions,":[124,194],"allowing":[125],"direct":[126],"sentiment-related":[130],"information":[131,447],"encoded.":[133],"It":[134],"also":[135,444],"supports":[136],"examination":[137,226],"independence":[139,191],"among":[140,192],"dimensions.":[141],"Multiple":[142],"configurations":[143],"different":[145],"sizes":[147],"are":[148,232,373],"evaluated":[149],"assess":[151],"trade-off":[153],"between":[154],"predictive":[155],"and":[157,168,190,224,243,290,300,329,344,363,366,404,416,426,450,461,490],"dimension":[158,238,324,339,388,398,410],"independence.":[159],"trained":[163],"Yelp":[165],"restaurant":[166],"reviews":[167],"baseline":[172],"model.":[173],"results":[175,254],"show":[176,255],"that":[177,216,256,267,307,386,432,455],"bottleneck-based":[179,477],"maintains":[181],"competitive":[182],"performance.":[183],"Based":[184],"evaluation":[187,310],"configuration":[196],"ten":[198],"dimensions":[200,266,276,294,352,372,420],"selected":[202],"for":[203,465],"detailed":[204],"analysis.":[205],"To":[206],"interpret":[207],"learned":[209],"representations,":[210],"an":[211],"integrated":[212],"framework":[213,464,478],"developed":[215],"combines":[217],"correlation":[218],"analysis,":[219,221],"contribution":[220],"regression":[222],"modeling,":[223],"qualitative":[225],"example":[228],"reviews.":[229],"These":[230,371,429],"methods":[231],"used":[233],"examine":[235,500],"each":[237,251,387],"relates":[239],"predictions":[242],"identify":[245],"linguistic":[247,270,392,507],"patterns":[248],"associated":[249,400],"dimension.":[252],"prediction":[258,291,315,336,434],"emerges":[259],"from":[260,378],"interaction":[262,358],"multiple":[264],"capture":[268,295,353],"distinct":[269],"patterns.":[271],"A":[272],"number":[274],"primary":[279],"factors":[280],"polarity,":[283],"exhibiting":[284],"strong":[285],"associations":[286],"classifier":[288],"outputs":[289],"decisions.":[292],"Other":[293,419],"discourse":[296,342,424],"structure,":[297],"narrative":[298,397],"styles,":[299],"stylistic":[301],"variations,":[302],"operating":[303],"secondary":[305],"signals":[306],"shape":[308],"expressed,":[312],"thereby":[313],"influencing":[314],"outcomes.":[316,337],"Specifically,":[317],"ten-dimensional":[320],"model,":[322],"one":[323],"captures":[325],"overall":[326],"evaluative":[327,439],"polarity":[328],"strongest":[332],"association":[333],"Another":[338],"reflects":[340],"complaint-related":[341],"structure":[343],"strongly":[346],"linked":[347,412],"negative":[349],"sentiment.":[350],"Additional":[351],"experiential":[354],"narrative,":[355],"aggregated":[356],"experiences,":[357],"service":[360],"staff,":[361],"advice":[362,409],"recommendation":[364],"language,":[365],"variation":[367],"expression":[369],"style.":[370],"not":[374,436],"predefined":[375],"but":[376,443],"emerge":[377],"during":[381],"training.":[382],"shows":[385],"aligns":[389],"specific":[391],"features.":[393],"For":[394],"example,":[395],"first-person":[402],"pronouns":[403],"past-tense":[405],"verbs,":[406],"while":[407],"imperative":[414],"expressions":[415],"second-person":[417],"pronouns.":[418],"reflect":[421],"differences":[422],"organization":[425],"structural":[427],"complexity.":[428],"findings":[430],"indicate":[431],"depends":[435],"only":[437],"words":[442],"structured":[449],"communicated.":[451],"demonstrates":[454],"architectural":[456],"can":[458,491],"improve":[459],"interpretability":[460],"provides":[462],"analyzing":[466],"at":[472],"representation":[474],"level.":[475],"introduced":[479],"designed":[484],"be":[486,492],"adaptable":[487],"across":[488],"domains":[489],"applied":[493],"other":[495],"text":[496],"organize":[506],"information.":[508]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-06-17T00:00:00"}