Comparative Study of Clustering Techniques for Short Text Documents. Rangrej, A., Kulkarni, S., & Tendulkar, A., V. Paper Website abstract bibtex We compare various document clustering techniques includ-ing K-means, SVD-based method and a graph-based ap-proach and their performance on short text data collected from Twitter. We define a measure for evaluating the cluster error with these techniques. Observations show that graph-based approach using affinity propagation performs best in clustering short text data with minimal cluster error.
@article{
title = {Comparative Study of Clustering Techniques for Short Text Documents},
type = {article},
keywords = {Clustering General Terms Algorithms,Experimentation Keywords clustering,K-means,SVD,affinity propagation,short text},
websites = {http://delivery.acm.org/10.1145/1970000/1963249/p111-rangrej.pdf?ip=128.227.12.255&id=1963249&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517857175_5974c3436fa634eab192eda6f1cd0d6b},
id = {ac5c6512-922f-3385-987e-7c141ed1aa55},
created = {2018-02-05T18:54:46.915Z},
accessed = {2018-02-05},
file_attached = {true},
profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},
group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},
last_modified = {2018-02-05T18:54:48.749Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
private_publication = {false},
abstract = {We compare various document clustering techniques includ-ing K-means, SVD-based method and a graph-based ap-proach and their performance on short text data collected from Twitter. We define a measure for evaluating the cluster error with these techniques. Observations show that graph-based approach using affinity propagation performs best in clustering short text data with minimal cluster error.},
bibtype = {article},
author = {Rangrej, Aniket and Kulkarni, Sayali and Tendulkar, Ashish V}
}
Downloads: 0
{"_id":"gNfzaakeA6avnhfx7","bibbaseid":"rangrej-kulkarni-tendulkar-comparativestudyofclusteringtechniquesforshorttextdocuments","downloads":0,"creationDate":"2018-02-07T16:22:57.332Z","title":"Comparative Study of Clustering Techniques for Short Text Documents","author_short":["Rangrej, A.","Kulkarni, S.","Tendulkar, A., V."],"year":null,"bibtype":"article","biburl":null,"bibdata":{"title":"Comparative Study of Clustering Techniques for Short Text Documents","type":"article","keywords":"Clustering General Terms Algorithms,Experimentation Keywords clustering,K-means,SVD,affinity propagation,short text","websites":"http://delivery.acm.org/10.1145/1970000/1963249/p111-rangrej.pdf?ip=128.227.12.255&id=1963249&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517857175_5974c3436fa634eab192eda6f1cd0d6b","id":"ac5c6512-922f-3385-987e-7c141ed1aa55","created":"2018-02-05T18:54:46.915Z","accessed":"2018-02-05","file_attached":"true","profile_id":"371589bb-c770-37ff-8193-93c6f25ffeb1","group_id":"f982cd63-7ceb-3aa2-ac7e-a953963d6716","last_modified":"2018-02-05T18:54:48.749Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"private_publication":false,"abstract":"We compare various document clustering techniques includ-ing K-means, SVD-based method and a graph-based ap-proach and their performance on short text data collected from Twitter. We define a measure for evaluating the cluster error with these techniques. Observations show that graph-based approach using affinity propagation performs best in clustering short text data with minimal cluster error.","bibtype":"article","author":"Rangrej, Aniket and Kulkarni, Sayali and Tendulkar, Ashish V","bibtex":"@article{\n title = {Comparative Study of Clustering Techniques for Short Text Documents},\n type = {article},\n keywords = {Clustering General Terms Algorithms,Experimentation Keywords clustering,K-means,SVD,affinity propagation,short text},\n websites = {http://delivery.acm.org/10.1145/1970000/1963249/p111-rangrej.pdf?ip=128.227.12.255&id=1963249&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517857175_5974c3436fa634eab192eda6f1cd0d6b},\n id = {ac5c6512-922f-3385-987e-7c141ed1aa55},\n created = {2018-02-05T18:54:46.915Z},\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 = {2018-02-05T18:54:48.749Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {We compare various document clustering techniques includ-ing K-means, SVD-based method and a graph-based ap-proach and their performance on short text data collected from Twitter. We define a measure for evaluating the cluster error with these techniques. Observations show that graph-based approach using affinity propagation performs best in clustering short text data with minimal cluster error.},\n bibtype = {article},\n author = {Rangrej, Aniket and Kulkarni, Sayali and Tendulkar, Ashish V}\n}","author_short":["Rangrej, A.","Kulkarni, S.","Tendulkar, A., V."],"urls":{"Paper":"http://bibbase.org/service/mendeley/371589bb-c770-37ff-8193-93c6f25ffeb1/file/00e329b0-6391-171b-2356-a7f217679893/Comparative_Study_of_Clustering_Techniques_for_Short_Text_Documents.pdf.pdf","Website":"http://delivery.acm.org/10.1145/1970000/1963249/p111-rangrej.pdf?ip=128.227.12.255&id=1963249&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517857175_5974c3436fa634eab192eda6f1cd0d6b"},"bibbaseid":"rangrej-kulkarni-tendulkar-comparativestudyofclusteringtechniquesforshorttextdocuments","role":"author","keyword":["Clustering General Terms Algorithms","Experimentation Keywords clustering","K-means","SVD","affinity propagation","short text"],"downloads":0},"search_terms":["comparative","study","clustering","techniques","short","text","documents","rangrej","kulkarni","tendulkar"],"keywords":["clustering general terms algorithms","experimentation keywords clustering","k-means","svd","affinity propagation","short text"],"authorIDs":[]}