Eintrag weiter verarbeiten
Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets
Gespeichert in:
Zeitschriftentitel: | Journal of the Association for Information Science and Technology |
---|---|
Personen und Körperschaften: | , , , |
In: | Journal of the Association for Information Science and Technology, 65, 2014, 7, S. 1416-1423 |
Format: | E-Article |
Sprache: | Englisch |
veröffentlicht: |
Wiley
|
Schlagwörter: |
author_facet |
Arakawa, Yui Kameda, Akihiro Aizawa, Akiko Suzuki, Takafumi Arakawa, Yui Kameda, Akihiro Aizawa, Akiko Suzuki, Takafumi |
---|---|
author |
Arakawa, Yui Kameda, Akihiro Aizawa, Akiko Suzuki, Takafumi |
spellingShingle |
Arakawa, Yui Kameda, Akihiro Aizawa, Akiko Suzuki, Takafumi Journal of the Association for Information Science and Technology Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets Library and Information Sciences Information Systems and Management Computer Networks and Communications Information Systems |
author_sort |
arakawa, yui |
spelling |
Arakawa, Yui Kameda, Akihiro Aizawa, Akiko Suzuki, Takafumi 2330-1635 2330-1643 Wiley Library and Information Sciences Information Systems and Management Computer Networks and Communications Information Systems http://dx.doi.org/10.1002/asi.23126 <jats:p>Recently, <jats:styled-content style="fixed-case">T</jats:styled-content>witter has received much attention, both from the general public and researchers, as a new method of transmitting information. Among others, the number of retweets (<jats:styled-content style="fixed-case">RTs</jats:styled-content>) and user types are the two important items of analysis for understanding the transmission of information on <jats:styled-content style="fixed-case">T</jats:styled-content>witter. To analyze this point, we applied text classification and feature extraction experiments using random forests machine learning with conventional stylistic and <jats:styled-content style="fixed-case">T</jats:styled-content>witter‐specific features. We first collected tweets from 40 accounts with a high number of followers and created tweet texts from 28,756 tweets. We then conducted 15 types of classification experiments using a variety of combinations of features such as function words, speech terms, <jats:styled-content style="fixed-case">T</jats:styled-content>witter's descriptive grammar, and information roles. We deliberately observed the effects of features for classification performance. The results indicated that class classification per user indicated the best performance. Furthermore, we observed that certain features had a greater impact on classification. In the case of the experiments that assessed the level of <jats:styled-content style="fixed-case">RT</jats:styled-content> quantity, information roles had an impact. In the case of user experiments, important features, such as the honorific postpositional particle and auxiliary verbs, such as “desu” and “masu,” had an impact. This research clarifies the features that are useful for categorizing tweets according to the number of <jats:styled-content style="fixed-case">RTs</jats:styled-content> and user types.</jats:p> Adding <scp>T</scp>witter‐specific features to stylistic features for classifying tweets by user type and number of retweets Journal of the Association for Information Science and Technology |
doi_str_mv |
10.1002/asi.23126 |
facet_avail |
Online |
finc_class_facet |
Allgemeines Informatik |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAwMi9hc2kuMjMxMjY |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAwMi9hc2kuMjMxMjY |
institution |
DE-D161 DE-Gla1 DE-Zi4 DE-15 DE-Pl11 DE-Rs1 DE-105 DE-14 FID-BBI-DE-23 DE-Ch1 DE-L229 DE-D275 DE-Bn3 DE-Brt1 |
imprint |
Wiley, 2014 |
imprint_str_mv |
Wiley, 2014 |
issn |
2330-1643 2330-1635 |
issn_str_mv |
2330-1643 2330-1635 |
language |
English |
mega_collection |
Wiley (CrossRef) |
match_str |
arakawa2014addingtwitterspecificfeaturestostylisticfeaturesforclassifyingtweetsbyusertypeandnumberofretweets |
publishDateSort |
2014 |
publisher |
Wiley |
recordtype |
ai |
record_format |
ai |
series |
Journal of the Association for Information Science and Technology |
source_id |
49 |
title |
Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_unstemmed |
Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_full |
Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_fullStr |
Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_full_unstemmed |
Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_short |
Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_sort |
adding <scp>t</scp>witter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
topic |
Library and Information Sciences Information Systems and Management Computer Networks and Communications Information Systems |
url |
http://dx.doi.org/10.1002/asi.23126 |
publishDate |
2014 |
physical |
1416-1423 |
description |
<jats:p>Recently, <jats:styled-content style="fixed-case">T</jats:styled-content>witter has received much attention, both from the general public and researchers, as a new method of transmitting information. Among others, the number of retweets (<jats:styled-content style="fixed-case">RTs</jats:styled-content>) and user types are the two important items of analysis for understanding the transmission of information on <jats:styled-content style="fixed-case">T</jats:styled-content>witter. To analyze this point, we applied text classification and feature extraction experiments using random forests machine learning with conventional stylistic and <jats:styled-content style="fixed-case">T</jats:styled-content>witter‐specific features. We first collected tweets from 40 accounts with a high number of followers and created tweet texts from 28,756 tweets. We then conducted 15 types of classification experiments using a variety of combinations of features such as function words, speech terms, <jats:styled-content style="fixed-case">T</jats:styled-content>witter's descriptive grammar, and information roles. We deliberately observed the effects of features for classification performance. The results indicated that class classification per user indicated the best performance. Furthermore, we observed that certain features had a greater impact on classification. In the case of the experiments that assessed the level of <jats:styled-content style="fixed-case">RT</jats:styled-content> quantity, information roles had an impact. In the case of user experiments, important features, such as the honorific postpositional particle and auxiliary verbs, such as “desu” and “masu,” had an impact. This research clarifies the features that are useful for categorizing tweets according to the number of <jats:styled-content style="fixed-case">RTs</jats:styled-content> and user types.</jats:p> |
container_issue |
7 |
container_start_page |
1416 |
container_title |
Journal of the Association for Information Science and Technology |
container_volume |
65 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792335222422896640 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T14:41:02.982Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Adding+Twitter%E2%80%90specific+features+to+stylistic+features+for+classifying+tweets+by+user+type+and+number+of+retweets&rft.date=2014-07-01&genre=article&issn=2330-1643&volume=65&issue=7&spage=1416&epage=1423&pages=1416-1423&jtitle=Journal+of+the+Association+for+Information+Science+and+Technology&atitle=Adding+%3Cscp%3ET%3C%2Fscp%3Ewitter%E2%80%90specific+features+to+stylistic+features+for+classifying+tweets+by+user+type+and+number+of+retweets&aulast=Suzuki&aufirst=Takafumi&rft_id=info%3Adoi%2F10.1002%2Fasi.23126&rft.language%5B0%5D=eng |
SOLR | |
_version_ | 1792335222422896640 |
author | Arakawa, Yui, Kameda, Akihiro, Aizawa, Akiko, Suzuki, Takafumi |
author_facet | Arakawa, Yui, Kameda, Akihiro, Aizawa, Akiko, Suzuki, Takafumi, Arakawa, Yui, Kameda, Akihiro, Aizawa, Akiko, Suzuki, Takafumi |
author_sort | arakawa, yui |
container_issue | 7 |
container_start_page | 1416 |
container_title | Journal of the Association for Information Science and Technology |
container_volume | 65 |
description | <jats:p>Recently, <jats:styled-content style="fixed-case">T</jats:styled-content>witter has received much attention, both from the general public and researchers, as a new method of transmitting information. Among others, the number of retweets (<jats:styled-content style="fixed-case">RTs</jats:styled-content>) and user types are the two important items of analysis for understanding the transmission of information on <jats:styled-content style="fixed-case">T</jats:styled-content>witter. To analyze this point, we applied text classification and feature extraction experiments using random forests machine learning with conventional stylistic and <jats:styled-content style="fixed-case">T</jats:styled-content>witter‐specific features. We first collected tweets from 40 accounts with a high number of followers and created tweet texts from 28,756 tweets. We then conducted 15 types of classification experiments using a variety of combinations of features such as function words, speech terms, <jats:styled-content style="fixed-case">T</jats:styled-content>witter's descriptive grammar, and information roles. We deliberately observed the effects of features for classification performance. The results indicated that class classification per user indicated the best performance. Furthermore, we observed that certain features had a greater impact on classification. In the case of the experiments that assessed the level of <jats:styled-content style="fixed-case">RT</jats:styled-content> quantity, information roles had an impact. In the case of user experiments, important features, such as the honorific postpositional particle and auxiliary verbs, such as “desu” and “masu,” had an impact. This research clarifies the features that are useful for categorizing tweets according to the number of <jats:styled-content style="fixed-case">RTs</jats:styled-content> and user types.</jats:p> |
doi_str_mv | 10.1002/asi.23126 |
facet_avail | Online |
finc_class_facet | Allgemeines, Informatik |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAwMi9hc2kuMjMxMjY |
imprint | Wiley, 2014 |
imprint_str_mv | Wiley, 2014 |
institution | DE-D161, DE-Gla1, DE-Zi4, DE-15, DE-Pl11, DE-Rs1, DE-105, DE-14, FID-BBI-DE-23, DE-Ch1, DE-L229, DE-D275, DE-Bn3, DE-Brt1 |
issn | 2330-1643, 2330-1635 |
issn_str_mv | 2330-1643, 2330-1635 |
language | English |
last_indexed | 2024-03-01T14:41:02.982Z |
match_str | arakawa2014addingtwitterspecificfeaturestostylisticfeaturesforclassifyingtweetsbyusertypeandnumberofretweets |
mega_collection | Wiley (CrossRef) |
physical | 1416-1423 |
publishDate | 2014 |
publishDateSort | 2014 |
publisher | Wiley |
record_format | ai |
recordtype | ai |
series | Journal of the Association for Information Science and Technology |
source_id | 49 |
spelling | Arakawa, Yui Kameda, Akihiro Aizawa, Akiko Suzuki, Takafumi 2330-1635 2330-1643 Wiley Library and Information Sciences Information Systems and Management Computer Networks and Communications Information Systems http://dx.doi.org/10.1002/asi.23126 <jats:p>Recently, <jats:styled-content style="fixed-case">T</jats:styled-content>witter has received much attention, both from the general public and researchers, as a new method of transmitting information. Among others, the number of retweets (<jats:styled-content style="fixed-case">RTs</jats:styled-content>) and user types are the two important items of analysis for understanding the transmission of information on <jats:styled-content style="fixed-case">T</jats:styled-content>witter. To analyze this point, we applied text classification and feature extraction experiments using random forests machine learning with conventional stylistic and <jats:styled-content style="fixed-case">T</jats:styled-content>witter‐specific features. We first collected tweets from 40 accounts with a high number of followers and created tweet texts from 28,756 tweets. We then conducted 15 types of classification experiments using a variety of combinations of features such as function words, speech terms, <jats:styled-content style="fixed-case">T</jats:styled-content>witter's descriptive grammar, and information roles. We deliberately observed the effects of features for classification performance. The results indicated that class classification per user indicated the best performance. Furthermore, we observed that certain features had a greater impact on classification. In the case of the experiments that assessed the level of <jats:styled-content style="fixed-case">RT</jats:styled-content> quantity, information roles had an impact. In the case of user experiments, important features, such as the honorific postpositional particle and auxiliary verbs, such as “desu” and “masu,” had an impact. This research clarifies the features that are useful for categorizing tweets according to the number of <jats:styled-content style="fixed-case">RTs</jats:styled-content> and user types.</jats:p> Adding <scp>T</scp>witter‐specific features to stylistic features for classifying tweets by user type and number of retweets Journal of the Association for Information Science and Technology |
spellingShingle | Arakawa, Yui, Kameda, Akihiro, Aizawa, Akiko, Suzuki, Takafumi, Journal of the Association for Information Science and Technology, Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets, Library and Information Sciences, Information Systems and Management, Computer Networks and Communications, Information Systems |
title | Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_full | Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_fullStr | Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_full_unstemmed | Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_short | Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_sort | adding <scp>t</scp>witter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
title_unstemmed | Adding Twitter‐specific features to stylistic features for classifying tweets by user type and number of retweets |
topic | Library and Information Sciences, Information Systems and Management, Computer Networks and Communications, Information Systems |
url | http://dx.doi.org/10.1002/asi.23126 |