Name-ethnicity classification from open sources. Ambekar, A., Ward, C., Mohammed, J., Male, S., & Skiena, S. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, of KDD '09, pages 49–58, New York, NY, USA, June, 2009. Association for Computing Machinery. ![Name-ethnicity classification from open sources [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The problem of ethnicity identification from names has a variety of important applications, including biomedical research, demographic studies, and marketing. Here we report on the development of an ethnicity classifier where all training data is extracted from public, non-confidential (and hence somewhat unreliable) sources. Our classifier uses hidden Markov models (HMMs) and decision trees to classify names into 13 cultural/ethnic groups with individual group accuracy comparable accuracy to earlier binary (e.g., Spanish/non-Spanish) classifiers. We have applied this classifier to over 20 million names from a large-scale news corpus, identifying interesting temporal and spatial trends on the representation of particular cultural/ethnic groups.
@inproceedings{ambekar_name-ethnicity_2009,
address = {New York, NY, USA},
series = {{KDD} '09},
title = {Name-ethnicity classification from open sources},
isbn = {978-1-60558-495-9},
url = {https://doi.org/10.1145/1557019.1557032},
doi = {10.1145/1557019.1557032},
abstract = {The problem of ethnicity identification from names has a variety of important applications, including biomedical research, demographic studies, and marketing. Here we report on the development of an ethnicity classifier where all training data is extracted from public, non-confidential (and hence somewhat unreliable) sources. Our classifier uses hidden Markov models (HMMs) and decision trees to classify names into 13 cultural/ethnic groups with individual group accuracy comparable accuracy to earlier binary (e.g., Spanish/non-Spanish) classifiers. We have applied this classifier to over 20 million names from a large-scale news corpus, identifying interesting temporal and spatial trends on the representation of particular cultural/ethnic groups.},
urldate = {2021-03-22},
booktitle = {Proceedings of the 15th {ACM} {SIGKDD} international conference on {Knowledge} discovery and data mining},
publisher = {Association for Computing Machinery},
author = {Ambekar, Anurag and Ward, Charles and Mohammed, Jahangir and Male, Swapna and Skiena, Steven},
month = jun,
year = {2009},
keywords = {ethnicity detection, name classification, news analysis, social science research},
pages = {49--58},
}
Downloads: 0
{"_id":"Mkxv7rzyJCswpbpSH","bibbaseid":"ambekar-ward-mohammed-male-skiena-nameethnicityclassificationfromopensources-2009","author_short":["Ambekar, A.","Ward, C.","Mohammed, J.","Male, S.","Skiena, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","series":"KDD '09","title":"Name-ethnicity classification from open sources","isbn":"978-1-60558-495-9","url":"https://doi.org/10.1145/1557019.1557032","doi":"10.1145/1557019.1557032","abstract":"The problem of ethnicity identification from names has a variety of important applications, including biomedical research, demographic studies, and marketing. Here we report on the development of an ethnicity classifier where all training data is extracted from public, non-confidential (and hence somewhat unreliable) sources. Our classifier uses hidden Markov models (HMMs) and decision trees to classify names into 13 cultural/ethnic groups with individual group accuracy comparable accuracy to earlier binary (e.g., Spanish/non-Spanish) classifiers. We have applied this classifier to over 20 million names from a large-scale news corpus, identifying interesting temporal and spatial trends on the representation of particular cultural/ethnic groups.","urldate":"2021-03-22","booktitle":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","publisher":"Association for Computing Machinery","author":[{"propositions":[],"lastnames":["Ambekar"],"firstnames":["Anurag"],"suffixes":[]},{"propositions":[],"lastnames":["Ward"],"firstnames":["Charles"],"suffixes":[]},{"propositions":[],"lastnames":["Mohammed"],"firstnames":["Jahangir"],"suffixes":[]},{"propositions":[],"lastnames":["Male"],"firstnames":["Swapna"],"suffixes":[]},{"propositions":[],"lastnames":["Skiena"],"firstnames":["Steven"],"suffixes":[]}],"month":"June","year":"2009","keywords":"ethnicity detection, name classification, news analysis, social science research","pages":"49–58","bibtex":"@inproceedings{ambekar_name-ethnicity_2009,\n\taddress = {New York, NY, USA},\n\tseries = {{KDD} '09},\n\ttitle = {Name-ethnicity classification from open sources},\n\tisbn = {978-1-60558-495-9},\n\turl = {https://doi.org/10.1145/1557019.1557032},\n\tdoi = {10.1145/1557019.1557032},\n\tabstract = {The problem of ethnicity identification from names has a variety of important applications, including biomedical research, demographic studies, and marketing. Here we report on the development of an ethnicity classifier where all training data is extracted from public, non-confidential (and hence somewhat unreliable) sources. Our classifier uses hidden Markov models (HMMs) and decision trees to classify names into 13 cultural/ethnic groups with individual group accuracy comparable accuracy to earlier binary (e.g., Spanish/non-Spanish) classifiers. We have applied this classifier to over 20 million names from a large-scale news corpus, identifying interesting temporal and spatial trends on the representation of particular cultural/ethnic groups.},\n\turldate = {2021-03-22},\n\tbooktitle = {Proceedings of the 15th {ACM} {SIGKDD} international conference on {Knowledge} discovery and data mining},\n\tpublisher = {Association for Computing Machinery},\n\tauthor = {Ambekar, Anurag and Ward, Charles and Mohammed, Jahangir and Male, Swapna and Skiena, Steven},\n\tmonth = jun,\n\tyear = {2009},\n\tkeywords = {ethnicity detection, name classification, news analysis, social science research},\n\tpages = {49--58},\n}\n\n\n\n\n\n\n\n","author_short":["Ambekar, A.","Ward, C.","Mohammed, J.","Male, S.","Skiena, S."],"key":"ambekar_name-ethnicity_2009","id":"ambekar_name-ethnicity_2009","bibbaseid":"ambekar-ward-mohammed-male-skiena-nameethnicityclassificationfromopensources-2009","role":"author","urls":{"Paper":"https://doi.org/10.1145/1557019.1557032"},"keyword":["ethnicity detection","name classification","news analysis","social science research"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/pab2163","dataSources":["fB4GuzdCZcPR6LeBn"],"keywords":["ethnicity detection","name classification","news analysis","social science research"],"search_terms":["name","ethnicity","classification","open","sources","ambekar","ward","mohammed","male","skiena"],"title":"Name-ethnicity classification from open sources","year":2009}