TRA CỨU
thông tin biểu ghi
  • Bài báo khoa học công nghệ
  • Ký hiệu PL/XG: 004
    Nhan đề: A STING algorithm and multi-dimensional vectors used for english sentiment classification in a distributed system /
ISSN 1941-7020
DDC 004
Nhan đề A STING algorithm and multi-dimensional vectors used for english sentiment classification in a distributed system / Vo Ngoc Phu, Vo Thi Ngoc Tran
Thông tin xuất bản 2017
Thông tin xuất bản Science Publications
Mô tả vật lý 19 p. ;
Tóm tắt Sentiment classification is significant in everyday life, such as in political activities, commodity production and commercial activities. Finding a fast, highly accurate solution to classify emotion has been a challenge for scientists. In this research, we have proposed a new model for Big Data sentiment classification in the parallel network environment - a Cloudera system with Hadoop Map (M) and Hadoop Reduce (R). Our new model has used a Statistical Information Grid Algorithm (STING) with multi-dimensional vector and 2,000,000 English documents of our English training data set for English document-level sentiment classification. Our new model can classify sentiment of millions of English documents based on many English documents in the parallel network environment. However, we tested our new model on our testing data set (including 1,000,000 English reviews, 500,000 positive and 500,000 negative) and achieved 83.92% accuracy.
Từ khóa tự do English Document Opinion Mining
Từ khóa tự do English Sentiment Classification
Từ khóa tự do Opinion Mining
Từ khóa tự do Sentiment Classification
Từ khóa tự do Distributed System
Từ khóa tự do Parallel System
Từ khóa tự do STING
Khoa Khoa Công nghệ Thông tin
Tác giả(bs) CN Vo, Thi Ngoc Tran
Tác giả(bs) CN Vo, Ngoc Phu
Nguồn trích . Số: Vol. 11, Issue 1, P. 19-37, ,
Nguồn trích American Journal of Engineering and Applied Sciences. , ,
Địa chỉ Thư Viện Đại học Nguyễn Tất Thành
Tệp tin điện tử https://thescipub.com/abstract/10.3844/ajeassp.2018.19.37
000 00000nam#a2200000u##4500
00119562
00212
00445AB5172-49A6-4BD7-995E-3DF672AC37B8
005202003090044
008200227s2017 xxu eng
0091 0
022 |a1941-7020
039|a20200309004436|bphucvh|c20200227143252|dphucvh|y20200226160200|zphucvh
040 |aNTT
041 |aeng
044 |avm
082|a004|223
245 |aA STING algorithm and multi-dimensional vectors used for english sentiment classification in a distributed system / |cVo Ngoc Phu, Vo Thi Ngoc Tran
260 |c2017
260|bScience Publications
300 |a19 p. ;
520 |aSentiment classification is significant in everyday life, such as in political activities, commodity production and commercial activities. Finding a fast, highly accurate solution to classify emotion has been a challenge for scientists. In this research, we have proposed a new model for Big Data sentiment classification in the parallel network environment - a Cloudera system with Hadoop Map (M) and Hadoop Reduce (R). Our new model has used a Statistical Information Grid Algorithm (STING) with multi-dimensional vector and 2,000,000 English documents of our English training data set for English document-level sentiment classification. Our new model can classify sentiment of millions of English documents based on many English documents in the parallel network environment. However, we tested our new model on our testing data set (including 1,000,000 English reviews, 500,000 positive and 500,000 negative) and achieved 83.92% accuracy.
653 |aEnglish Document Opinion Mining
653 |aEnglish Sentiment Classification
653 |aOpinion Mining
653 |aSentiment Classification
653|aDistributed System
653|aParallel System
653|aSTING
690|aKhoa Công nghệ Thông tin
700 |aVo, Thi Ngoc Tran
700|aVo, Ngoc Phu
773|gVol. 11, Issue 1, P. 19-37
773|tAmerican Journal of Engineering and Applied Sciences
852 |aThư Viện Đại học Nguyễn Tất Thành
856|uhttps://thescipub.com/abstract/10.3844/ajeassp.2018.19.37
890|c1|a0|b0|d1
Không tìm thấy biểu ghi nào