A Dirichlet Multinomial Mixture Model-based Approach for Short Text Clustering. Yin, J. & Wang, J. Paper Website abstract bibtex Short text clustering has become an increasingly impor-tant task with the popularity of social media like Twitter, Google+, and Facebook. It is a challenging problem due to its sparse, high-dimensional, and large-volume characteris-tics. In this paper, we proposed a collapsed Gibbs Sampling algorithm for the Dirichlet Multinomial Mixture model for short text clustering (abbr. to GSDMM). We found that GS-DMM can infer the number of clusters automatically with a good balance between the completeness and homogeneity of the clustering results, and is fast to converge. GSDMM can also cope with the sparse and high-dimensional problem of short texts, and can obtain the representative words of each cluster. Our extensive experimental study shows that GSDMM can achieve significantly better performance than three other clustering models.
@article{
title = {A Dirichlet Multinomial Mixture Model-based Approach for Short Text Clustering},
type = {article},
identifiers = {[object Object]},
keywords = {Dirichlet Multinomial Mixture,Gibbs Sampling},
websites = {http://delivery.acm.org/10.1145/2630000/2623715/p233-yin.pdf?ip=128.227.11.255&id=2623715&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517852838_aec0efe8025aed3ace29dd85e84c60a5},
id = {fb3d2c4d-a2f9-3fa3-82b0-99809227c50d},
created = {2018-02-05T17:42:26.831Z},
accessed = {2018-02-05},
file_attached = {true},
profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},
group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},
last_modified = {2018-02-05T17:42:29.786Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
private_publication = {false},
abstract = {Short text clustering has become an increasingly impor-tant task with the popularity of social media like Twitter, Google+, and Facebook. It is a challenging problem due to its sparse, high-dimensional, and large-volume characteris-tics. In this paper, we proposed a collapsed Gibbs Sampling algorithm for the Dirichlet Multinomial Mixture model for short text clustering (abbr. to GSDMM). We found that GS-DMM can infer the number of clusters automatically with a good balance between the completeness and homogeneity of the clustering results, and is fast to converge. GSDMM can also cope with the sparse and high-dimensional problem of short texts, and can obtain the representative words of each cluster. Our extensive experimental study shows that GSDMM can achieve significantly better performance than three other clustering models.},
bibtype = {article},
author = {Yin, Jianhua and Wang, Jianyong}
}
Downloads: 0
{"_id":"Y3eA756Rcw9FSB7ta","bibbaseid":"yin-wang-adirichletmultinomialmixturemodelbasedapproachforshorttextclustering","downloads":0,"creationDate":"2018-02-07T16:22:57.299Z","title":"A Dirichlet Multinomial Mixture Model-based Approach for Short Text Clustering","author_short":["Yin, J.","Wang, J."],"year":null,"bibtype":"article","biburl":null,"bibdata":{"title":"A Dirichlet Multinomial Mixture Model-based Approach for Short Text Clustering","type":"article","identifiers":"[object Object]","keywords":"Dirichlet Multinomial Mixture,Gibbs Sampling","websites":"http://delivery.acm.org/10.1145/2630000/2623715/p233-yin.pdf?ip=128.227.11.255&id=2623715&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517852838_aec0efe8025aed3ace29dd85e84c60a5","id":"fb3d2c4d-a2f9-3fa3-82b0-99809227c50d","created":"2018-02-05T17:42:26.831Z","accessed":"2018-02-05","file_attached":"true","profile_id":"371589bb-c770-37ff-8193-93c6f25ffeb1","group_id":"f982cd63-7ceb-3aa2-ac7e-a953963d6716","last_modified":"2018-02-05T17:42:29.786Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"private_publication":false,"abstract":"Short text clustering has become an increasingly impor-tant task with the popularity of social media like Twitter, Google+, and Facebook. It is a challenging problem due to its sparse, high-dimensional, and large-volume characteris-tics. In this paper, we proposed a collapsed Gibbs Sampling algorithm for the Dirichlet Multinomial Mixture model for short text clustering (abbr. to GSDMM). We found that GS-DMM can infer the number of clusters automatically with a good balance between the completeness and homogeneity of the clustering results, and is fast to converge. GSDMM can also cope with the sparse and high-dimensional problem of short texts, and can obtain the representative words of each cluster. Our extensive experimental study shows that GSDMM can achieve significantly better performance than three other clustering models.","bibtype":"article","author":"Yin, Jianhua and Wang, Jianyong","bibtex":"@article{\n title = {A Dirichlet Multinomial Mixture Model-based Approach for Short Text Clustering},\n type = {article},\n identifiers = {[object Object]},\n keywords = {Dirichlet Multinomial Mixture,Gibbs Sampling},\n websites = {http://delivery.acm.org/10.1145/2630000/2623715/p233-yin.pdf?ip=128.227.11.255&id=2623715&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517852838_aec0efe8025aed3ace29dd85e84c60a5},\n id = {fb3d2c4d-a2f9-3fa3-82b0-99809227c50d},\n created = {2018-02-05T17:42:26.831Z},\n accessed = {2018-02-05},\n file_attached = {true},\n profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},\n group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},\n last_modified = {2018-02-05T17:42:29.786Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {Short text clustering has become an increasingly impor-tant task with the popularity of social media like Twitter, Google+, and Facebook. It is a challenging problem due to its sparse, high-dimensional, and large-volume characteris-tics. In this paper, we proposed a collapsed Gibbs Sampling algorithm for the Dirichlet Multinomial Mixture model for short text clustering (abbr. to GSDMM). We found that GS-DMM can infer the number of clusters automatically with a good balance between the completeness and homogeneity of the clustering results, and is fast to converge. GSDMM can also cope with the sparse and high-dimensional problem of short texts, and can obtain the representative words of each cluster. Our extensive experimental study shows that GSDMM can achieve significantly better performance than three other clustering models.},\n bibtype = {article},\n author = {Yin, Jianhua and Wang, Jianyong}\n}","author_short":["Yin, J.","Wang, J."],"urls":{"Paper":"http://bibbase.org/service/mendeley/371589bb-c770-37ff-8193-93c6f25ffeb1/file/062a476b-baae-904f-74c6-a560c4a79ddb/A_Dirichlet_Multinomial_Mixture_Model-based_Approach_for_Short_Text_Clustering.pdf.pdf","Website":"http://delivery.acm.org/10.1145/2630000/2623715/p233-yin.pdf?ip=128.227.11.255&id=2623715&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517852838_aec0efe8025aed3ace29dd85e84c60a5"},"bibbaseid":"yin-wang-adirichletmultinomialmixturemodelbasedapproachforshorttextclustering","role":"author","keyword":["Dirichlet Multinomial Mixture","Gibbs Sampling"],"downloads":0,"html":""},"search_terms":["dirichlet","multinomial","mixture","model","based","approach","short","text","clustering","yin","wang"],"keywords":["dirichlet multinomial mixture","gibbs sampling"],"authorIDs":[]}