{"id":"https://openalex.org/W4281702629","doi":"https://doi.org/10.48550/arxiv.2206.00773","title":"Assessing the trade-off between prediction accuracy and interpretability for topic modeling on energetic materials corpora","display_name":"Assessing the trade-off between prediction accuracy and interpretability for topic modeling on energetic materials corpora","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4281702629","doi":"https://doi.org/10.48550/arxiv.2206.00773"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.00773","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00773","pdf_url":"https://arxiv.org/pdf/2206.00773","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.00773","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078827360","display_name":"Monica Puerto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I181401687","display_name":"American University","ror":"https://ror.org/052w4zt36","country_code":"US","type":"education","lineage":["https://openalex.org/I181401687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puerto, Monica","raw_affiliation_strings":["American University , Washington , D.C. 20016 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University , Washington , D.C. 20016 , USA","institution_ids":["https://openalex.org/I181401687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045205640","display_name":"Mason Kellett","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I181401687","display_name":"American University","ror":"https://ror.org/052w4zt36","country_code":"US","type":"education","lineage":["https://openalex.org/I181401687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kellett, Mason","raw_affiliation_strings":["American University , Washington , D.C. 20016 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University , Washington , D.C. 20016 , USA","institution_ids":["https://openalex.org/I181401687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031793157","display_name":"Rodanthi Nikopoulou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I181401687","display_name":"American University","ror":"https://ror.org/052w4zt36","country_code":"US","type":"education","lineage":["https://openalex.org/I181401687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikopoulou, Rodanthi","raw_affiliation_strings":["American University , Washington , D.C. 20016 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University , Washington , D.C. 20016 , USA","institution_ids":["https://openalex.org/I181401687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036788329","display_name":"Mark Fuge","orcid":"https://orcid.org/0000-0003-3819-8895","observed_orcids":["https://orcid.org/0000-0003-3819-8895"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuge, Mark D.","raw_affiliation_strings":["Center for Engineering Concepts Development , Department of Mechanical Engineering , University of Maryland , College Park , MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Engineering Concepts Development , Department of Mechanical Engineering , University of Maryland , College Park , MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036198087","display_name":"Ruth M. Doherty","orcid":"https://orcid.org/0000-0001-7601-2209","observed_orcids":["https://orcid.org/0000-0001-7601-2209","https://orcid.org/0009-0000-3994-5675"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doherty, Ruth","raw_affiliation_strings":["Energetics Technology Center , Indian Head , MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Energetics Technology Center , Indian Head , MD","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101476638","display_name":"Peter W. Chung","orcid":"https://orcid.org/0000-0002-3276-5994","observed_orcids":["https://orcid.org/0000-0002-3276-5994"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung, Peter W.","raw_affiliation_strings":["Center for Engineering Concepts Development , Department of Mechanical Engineering , University of Maryland , College Park , MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Engineering Concepts Development , Department of Mechanical Engineering , University of Maryland , College Park , MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006915006","display_name":"Zois Boukouvalas","orcid":"https://orcid.org/0000-0002-5131-1891","observed_orcids":["https://orcid.org/0000-0002-5131-1891"]},"institutions":[{"id":"https://openalex.org/I181401687","display_name":"American University","ror":"https://ror.org/052w4zt36","country_code":"US","type":"education","lineage":["https://openalex.org/I181401687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boukouvalas, Zois","raw_affiliation_strings":["American University , Washington , D.C. 20016 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University , Washington , D.C. 20016 , USA","institution_ids":["https://openalex.org/I181401687"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10028","display_name":"Topic Modeling","score":0.475600004196167,"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/T10028","display_name":"Topic Modeling","score":0.475600004196167,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.21089999377727509,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12099999934434891,"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/topic-modeling","display_name":"topic modeling","score":0.9279999732971191},{"id":"https://openalex.org/keywords/energetic-materials","display_name":"energetic materials","score":0.9639999866485596},{"id":"https://openalex.org/keywords/document-embeddings","display_name":"document embeddings","score":0.7210000157356262},{"id":"https://openalex.org/keywords/lime","display_name":"lime","score":0.6769999861717224},{"id":"https://openalex.org/keywords/model-agnostic-explanation","display_name":"model-agnostic explanation","score":0.8050000071525574},{"id":"https://openalex.org/keywords/document-classification","display_name":"document classification","score":0.5199999809265137},{"id":"https://openalex.org/keywords/scientific-text-analysis","display_name":"scientific text analysis","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9160398840904236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380682826042175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5952437520027161},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5577036738395691},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5178189873695374},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5130997896194458},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5083572268486023},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.500769853591919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49508586525917053},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4548332393169403},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42296522855758667},{"id":"https://openalex.org/C97514900","wikidata":"https://www.wikidata.org/wiki/Q719597","display_name":"Energetics","level":2,"score":0.41955041885375977},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4137153923511505},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.00773","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00773","pdf_url":"https://arxiv.org/pdf/2206.00773","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2206.00773","doi":"https://doi.org/10.48550/arxiv.2206.00773","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.00773","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.00773","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.00773","pdf_url":"https://arxiv.org/pdf/2206.00773","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G94973616","display_name":null,"funder_award_id":"N00014-21-C-1016","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387422945","https://openalex.org/W4391836019","https://openalex.org/W7143298528","https://openalex.org/W2894289927","https://openalex.org/W4385484300","https://openalex.org/W6888843937","https://openalex.org/W2598794633","https://openalex.org/W4401067497","https://openalex.org/W2463552202","https://openalex.org/W214705575"],"abstract_inverted_index":{"As":[0],"the":[1,37,59,72,82,85,92],"amount":[2],"and":[3,33,79,97,133,156],"variety":[4],"of":[5,22,29,39,61,122,130,141,161],"energetics":[6,43,142,153,162],"research":[7,18,44],"increases,":[8],"machine":[9],"aware":[10],"topic":[11,25],"identification":[12,26],"is":[13],"necessary":[14,56],"to":[15,57,125,134],"streamline":[16],"future":[17],"pipelines.":[19],"The":[20],"makeup":[21],"an":[23],"automatic":[24],"process":[27],"consists":[28],"creating":[30],"document":[31,63,69,102],"representations":[32],"performing":[34],"classification.":[35],"However,":[36],"implementation":[38],"these":[40],"processes":[41],"on":[42,149],"imposes":[45],"new":[46],"challenges.":[47],"Energetics":[48],"datasets":[49],"contain":[50],"many":[51],"scientific":[52],"terms":[53],"that":[54,105],"are":[55],"understand":[58],"context":[60],"a":[62,127,150],"but":[64],"may":[65],"require":[66],"more":[67],"complex":[68],"representations.":[70],"Secondly,":[71],"predictions":[73],"from":[74],"classification":[75],"must":[76],"be":[77],"understandable":[78],"trusted":[80],"by":[81,99,158],"chemists":[83],"within":[84],"pipeline.":[86],"In":[87],"this":[88],"work,":[89],"we":[90,114],"study":[91,145],"trade-off":[93],"between":[94],"prediction":[95,124,132],"accuracy":[96,112],"interpretability":[98,118],"implementing":[100],"three":[101],"embedding":[103],"methods":[104],"vary":[106],"in":[107],"computational":[108],"complexity.":[109],"With":[110],"our":[111,139,159],"results,":[113],"also":[115],"introduce":[116],"local":[117],"model-agnostic":[119],"explanations":[120],"(LIME)":[121],"each":[123,131],"provide":[126],"localized":[128],"understanding":[129],"validate":[135],"classifier":[136],"decisions":[137],"with":[138],"team":[140,160],"experts.":[143,163],"This":[144],"was":[146],"carried":[147],"out":[148],"novel":[151],"labeled":[152],"dataset":[154],"created":[155],"validated":[157]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2022-06-13T00:00:00"}