Ngôn ngữ:

Microblog language identification: overcoming the limitations of short, unedited and idiomatic text

Language Resources and Evaluation, 2013-03, Vol.47 (1), p.195-215 [Tạp chí có phản biện]

2013 Springer Science+Business Media ;The Author(s) 2012 ;Springer Science+Business Media Dordrecht 2013 ;ISSN: 1574-020X ;EISSN: 1572-8412 ;EISSN: 1574-0218 ;DOI: 10.1007/s10579-012-9195-y ;CODEN: COHUAD

Tài liệu số/Tài liệu điện tử

Trích dẫn Trích dẫn bởi

Gửi đến

Nhan đề:
Microblog language identification: overcoming the limitations of short, unedited and idiomatic text
Tác giả: Carter, Simon ; Weerkamp, Wouter ; Tsagkias, Manos
Chủ đề: Artificial intelligence ; Artificial languages ; Blogs ; Classification ; Computational Linguistics ; Computer Science ; Content analysis ; Conversation ; Correlation analysis ; Dutch language ; English ; French language ; German ; Hyperlinks ; Identification methods ; Idioms ; Language ; Language and Literature ; Language identification ; Language usage ; Languages ; Linguistics ; Links ; Majority voting ; Metadata ; Microblogs ; Multilingualism ; Nonnative languages ; Platforms ; Social media ; Social Sciences ; Space ; Spanish ; Special Issue: Analysis of Short Texts on the Web ; State of the art ; Temporal logic ; Texts ; Training
Là 1 phần của: Language Resources and Evaluation, 2013-03, Vol.47 (1), p.195-215
Mô tả: Multilingual posts can potentially affect the outcomes of content analysis on microblog platforms. To this end, language identification can provide a monolingual set of content for analysis. We find the unedited and idiomatic language of microblogs to be challenging for state-of-the-art language identification methods. To account for this, we identify five microblog characteristics that can help in language identification: the language profile of the blogger (blogger), the content of an attached hyperlink (link), the language profile of other users mentioned (mention) in the post, the language profile of a tag (tag), and the language of the original post (conversation), if the post we examine is a reply. Further, we present methods that combine these priors in a post-dependent and post-independent way. We present test results on 1,000 posts from five languages (Dutch, English, French, German, and Spanish), which show that our priors improve accuracy by 5 % over a domain specific baseline, and show that post-dependent combination of the priors achieves the best performance. When suitable training data does not exist, our methods still outperform a domain unspecific baseline. We conclude with an examination of the language distribution of a million tweets, along with temporal analysis, the usage of twitter features across languages, and a correlation study between classifications made and geo-location and language metadata fields.
Nơi xuất bản: Dordrecht: Springer
Ngôn ngữ: English
Số nhận dạng: ISSN: 1574-020X
EISSN: 1572-8412
EISSN: 1574-0218
DOI: 10.1007/s10579-012-9195-y
CODEN: COHUAD
Nguồn: Alma/SFX Local Collection
Springer Nature OA/Free Journals
ProQuest Central

Trở lại danh sách kết quả

Trước Kết quả 18 Tiếp theo Tới trang tiếp theo


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Microblog language identification: overcoming the limitations of short, unedited and idiomatic text

2013 Springer Science+Business Media ;The Author(s) 2012 ;Springer Science+Business Media Dordrecht 2013 ;ISSN: 1574-020X ;EISSN: 1572-8412 ;EISSN: 1574-0218 ;DOI: 10.1007/s10579-012-9195-y ;CODEN: COHUAD

Đang tìm Cơ sở dữ liệu bên ngoài...