{"id":"https://openalex.org/W4313563829","doi":"https://doi.org/10.1145/3551349.3559508","title":"\u2018Who built this crap?\u2019 Developing a Software Engineering Domain Specific Toxicity Detector","display_name":"\u2018Who built this crap?\u2019 Developing a Software Engineering Domain Specific Toxicity Detector","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4313563829","doi":"https://doi.org/10.1145/3551349.3559508"},"language":"en","primary_location":{"id":"doi:10.1145/3551349.3559508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3559508","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3559508","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3559508","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082753461","display_name":"Jaydeb Sarker","orcid":"https://orcid.org/0000-0001-6440-7596"},"institutions":[{"id":"https://openalex.org/I125866687","display_name":"Wayne State College","ror":"https://ror.org/02cntrd02","country_code":"US","type":"education","lineage":["https://openalex.org/I125866687"]},{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaydeb Sarker","raw_affiliation_strings":["Computer Science, Wayne State University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Wayne State University, United States","institution_ids":["https://openalex.org/I125866687","https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082753461"],"corresponding_institution_ids":["https://openalex.org/I125866687","https://openalex.org/I185443292"],"apc_list":null,"apc_paid":null,"fwci":1.0048,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78666026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9825000166893005,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/toxicity","display_name":"Toxicity","score":0.6787028312683105},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.674660325050354},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.613257110118866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6014326214790344},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5509844422340393},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5493981838226318},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.41110140085220337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3595123887062073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.344340980052948},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3302602171897888},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25388360023498535},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1692052185535431},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1571005880832672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09295329451560974}],"concepts":[{"id":"https://openalex.org/C29730261","wikidata":"https://www.wikidata.org/wiki/Q274160","display_name":"Toxicity","level":2,"score":0.6787028312683105},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.674660325050354},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.613257110118866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6014326214790344},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5509844422340393},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5493981838226318},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.41110140085220337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3595123887062073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.344340980052948},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3302602171897888},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25388360023498535},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1692052185535431},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1571005880832672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09295329451560974},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551349.3559508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3559508","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3559508","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3551349.3559508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3559508","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3559508","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1519052312","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2740721704","https://openalex.org/W2904388869","https://openalex.org/W2949785398","https://openalex.org/W2963748066","https://openalex.org/W3090115945","https://openalex.org/W3090254769","https://openalex.org/W3134691252","https://openalex.org/W3194283088","https://openalex.org/W4283203903","https://openalex.org/W4284672755","https://openalex.org/W4309618999"],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W2323648130","https://openalex.org/W2157140558","https://openalex.org/W2378782423","https://openalex.org/W2366906938","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W4233308809","https://openalex.org/W2388988621","https://openalex.org/W2000775715"],"abstract_inverted_index":{"Since":[0],"toxicity":[1,18,34,53,102],"during":[2],"developers\u2019":[3,15],"interactions":[4],"in":[5],"open":[6],"source":[7],"software":[8],"(OSS)":[9],"projects":[10],"show":[11],"negative":[12],"impacts":[13],"on":[14],"relation,":[16],"a":[17,51],"detector":[19,54],"for":[20],"the":[21,40],"Software":[22],"Engineering":[23],"(SE)":[24],"domain":[25],"is":[26,56],"needed.":[27],"However,":[28],"prior":[29],"studies":[30],"found":[31,96],"that":[32,55,97],"contemporary":[33],"detection":[35],"tools":[36],"performed":[37],"poorly":[38],"with":[39,58,68,104],"SE":[41,87],"texts.":[42],"To":[43],"address":[44],"this":[45],"challenge,":[46],"I":[47,65,94],"have":[48,95],"developed":[49],"ToxiCR,":[50],"SE-specific":[52],"evaluated":[57],"manually":[59],"labeled":[60],"19,571":[61],"code":[62],"review":[63],"comments.":[64],"evaluate":[66],"ToxiCR":[67,98],"different":[69],"combinations":[70],"of":[71,84,106,112],"ten":[72],"supervised":[73],"learning":[74],"models,":[75],"five":[76],"text":[77],"vectorizers,":[78],"and":[79,108],"eight":[80],"preprocessing":[81],"techniques":[82],"(two":[83],"them":[85],"are":[86],"domain-specific).":[88],"After":[89],"applying":[90],"all":[91],"possible":[92],"combinations,":[93],"significantly":[99],"outperformed":[100],"existing":[101],"classifiers":[103],"accuracy":[105],"95.8%":[107],"an":[109],"F1":[110],"score":[111],"88.9%.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
