Extracting descriptions of problems with product and services from twitter data

Extracting descriptions of problems with product and services from twitter data. Gupta, N., K. Word Journal Of The International Linguistic Association, 2010.
abstract bibtex

There is enough evidence that social media contains timely infor- mation that businesses could use to their beneﬁts. In this paper we discuss automatic extraction of descriptions of problems from twit- ter data. More speciﬁcally we present a system that ﬁlters tweets related to an enterprise and extracts descriptions of problems with their product/service. First step of this extraction process is to iden- tify the tweets containing such descriptions. We view this as text classiﬁcation problem. We propose that sentences describing prob- lems can be characterized by their lexical and syntactic structure. Our experiments show that use of such structural features in classi- ﬁcation models, results in the F-measure of 0.742. It is a signiﬁcant improvement over a baseline F-measure of 0.66, obtained by using only word ngram features. Since twitter data is dynamic, classiﬁca- tion models have to be adopted to changing nature of problems and language distributions. We describe a simple adaptation scheme, and experimentally demonstrate its effectiveness. Finally we dis- cuss our method to pinpoint the phrases describing the problems in the identiﬁed tweets. We show that by using simple syntactic pat- tern an extraction F-measure of 0.434 is achieved. Considering the noise in the tweeter data this level of performance is quite encour- aging.

@article{
 title = {Extracting descriptions of problems with product and services from twitter data},
 type = {article},
 year = {2010},
 id = {e088b68f-6834-3036-86f3-6c8b62bc5c69},
 created = {2012-02-28T00:52:49.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 tags = {twitter},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Gupta2010},
 private_publication = {false},
 abstract = {There is enough evidence that social media contains timely infor- mation that businesses could use to their beneﬁts. In this paper we discuss automatic extraction of descriptions of problems from twit- ter data. More speciﬁcally we present a system that ﬁlters tweets related to an enterprise and extracts descriptions of problems with their product/service. First step of this extraction process is to iden- tify the tweets containing such descriptions. We view this as text classiﬁcation problem. We propose that sentences describing prob- lems can be characterized by their lexical and syntactic structure. Our experiments show that use of such structural features in classi- ﬁcation models, results in the F-measure of 0.742. It is a signiﬁcant improvement over a baseline F-measure of 0.66, obtained by using only word ngram features. Since twitter data is dynamic, classiﬁca- tion models have to be adopted to changing nature of problems and language distributions. We describe a simple adaptation scheme, and experimentally demonstrate its effectiveness. Finally we dis- cuss our method to pinpoint the phrases describing the problems in the identiﬁed tweets. We show that by using simple syntactic pat- tern an extraction F-measure of 0.434 is achieved. Considering the noise in the tweeter data this level of performance is quite encour- aging.},
 bibtype = {article},
 author = {Gupta, Narendra K},
 journal = {Word Journal Of The International Linguistic Association},
 number = {September}
}

Downloads: 0

{"_id":"XMwF293xbtahZTH88","bibbaseid":"gupta-extractingdescriptionsofproblemswithproductandservicesfromtwitterdata-2010","authorIDs":[],"author_short":["Gupta, N., K."],"bibdata":{"title":"Extracting descriptions of problems with product and services from twitter data","type":"article","year":"2010","id":"e088b68f-6834-3036-86f3-6c8b62bc5c69","created":"2012-02-28T00:52:49.000Z","file_attached":false,"profile_id":"5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6","group_id":"066b42c8-f712-3fc3-abb2-225c158d2704","last_modified":"2017-03-14T14:36:19.698Z","tags":"twitter","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Gupta2010","private_publication":false,"abstract":"There is enough evidence that social media contains timely infor- mation that businesses could use to their beneﬁts. In this paper we discuss automatic extraction of descriptions of problems from twit- ter data. More speciﬁcally we present a system that ﬁlters tweets related to an enterprise and extracts descriptions of problems with their product/service. First step of this extraction process is to iden- tify the tweets containing such descriptions. We view this as text classiﬁcation problem. We propose that sentences describing prob- lems can be characterized by their lexical and syntactic structure. Our experiments show that use of such structural features in classi- ﬁcation models, results in the F-measure of 0.742. It is a signiﬁcant improvement over a baseline F-measure of 0.66, obtained by using only word ngram features. Since twitter data is dynamic, classiﬁca- tion models have to be adopted to changing nature of problems and language distributions. We describe a simple adaptation scheme, and experimentally demonstrate its effectiveness. Finally we dis- cuss our method to pinpoint the phrases describing the problems in the identiﬁed tweets. We show that by using simple syntactic pat- tern an extraction F-measure of 0.434 is achieved. Considering the noise in the tweeter data this level of performance is quite encour- aging.","bibtype":"article","author":"Gupta, Narendra K","journal":"Word Journal Of The International Linguistic Association","number":"September","bibtex":"@article{\n title = {Extracting descriptions of problems with product and services from twitter data},\n type = {article},\n year = {2010},\n id = {e088b68f-6834-3036-86f3-6c8b62bc5c69},\n created = {2012-02-28T00:52:49.000Z},\n file_attached = {false},\n profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},\n group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},\n last_modified = {2017-03-14T14:36:19.698Z},\n tags = {twitter},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Gupta2010},\n private_publication = {false},\n abstract = {There is enough evidence that social media contains timely infor- mation that businesses could use to their beneﬁts. In this paper we discuss automatic extraction of descriptions of problems from twit- ter data. More speciﬁcally we present a system that ﬁlters tweets related to an enterprise and extracts descriptions of problems with their product/service. First step of this extraction process is to iden- tify the tweets containing such descriptions. We view this as text classiﬁcation problem. We propose that sentences describing prob- lems can be characterized by their lexical and syntactic structure. Our experiments show that use of such structural features in classi- ﬁcation models, results in the F-measure of 0.742. It is a signiﬁcant improvement over a baseline F-measure of 0.66, obtained by using only word ngram features. Since twitter data is dynamic, classiﬁca- tion models have to be adopted to changing nature of problems and language distributions. We describe a simple adaptation scheme, and experimentally demonstrate its effectiveness. Finally we dis- cuss our method to pinpoint the phrases describing the problems in the identiﬁed tweets. We show that by using simple syntactic pat- tern an extraction F-measure of 0.434 is achieved. Considering the noise in the tweeter data this level of performance is quite encour- aging.},\n bibtype = {article},\n author = {Gupta, Narendra K},\n journal = {Word Journal Of The International Linguistic Association},\n number = {September}\n}","author_short":["Gupta, N., K."],"bibbaseid":"gupta-extractingdescriptionsofproblemswithproductandservicesfromtwitterdata-2010","role":"author","urls":{},"downloads":0,"html":""},"bibtype":"article","creationDate":"2020-02-06T23:48:12.262Z","downloads":0,"keywords":[],"search_terms":["extracting","descriptions","problems","product","services","twitter","data","gupta"],"title":"Extracting descriptions of problems with product and services from twitter data","year":2010}