TY - GEN
T1 - Application of 2-gram to English Q&A Statements to Obtain Factor Scores
AU - Yokoyama, Yuya
AU - Hochin, Teruhisa
AU - Nomiya, Hiroki
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In order to solve the issues of mismatches between the intentions of questioners and respondents of Question and Answer (Q&A) sites, impression evaluation experiments have resulted in obtaining nine factors of impressions for Japanese Q&A statements. The feature values of syntactic information were initially extracted through morphological analysis and utilized for multiple regression analysis to obtain factor scores for any Q&A statements. The calculation of factor scores has also been realized by extracting syntactic information through N-gram applied to Part-of-Speech extracted by way of morphological analysis. However, most of our methods so far have been dependent on Japanese, and so we need to validate if our method can be extended to other languages as well. So far, in a similar way as in Japanese, the nine factors have also experimentally been obtained from English Q&A statements. It was confirmed as well that the factor scores were calculated using the feature values of English statements extracted through morphological analysis. Therefore, in this paper, 2-gram as well as morphological analysis was applied to the feature values of English Q&A statements. As a result of multiple regression analysis, it has been shown that the application of 2-gram would result in as good an accuracy as morphological analysis for all nine factors. Therefore, it could be concluded that 2-gram would be applicable to our method in English as well.
AB - In order to solve the issues of mismatches between the intentions of questioners and respondents of Question and Answer (Q&A) sites, impression evaluation experiments have resulted in obtaining nine factors of impressions for Japanese Q&A statements. The feature values of syntactic information were initially extracted through morphological analysis and utilized for multiple regression analysis to obtain factor scores for any Q&A statements. The calculation of factor scores has also been realized by extracting syntactic information through N-gram applied to Part-of-Speech extracted by way of morphological analysis. However, most of our methods so far have been dependent on Japanese, and so we need to validate if our method can be extended to other languages as well. So far, in a similar way as in Japanese, the nine factors have also experimentally been obtained from English Q&A statements. It was confirmed as well that the factor scores were calculated using the feature values of English statements extracted through morphological analysis. Therefore, in this paper, 2-gram as well as morphological analysis was applied to the feature values of English Q&A statements. As a result of multiple regression analysis, it has been shown that the application of 2-gram would result in as good an accuracy as morphological analysis for all nine factors. Therefore, it could be concluded that 2-gram would be applicable to our method in English as well.
KW - 2-gram
KW - English
KW - Factor Score
KW - Multiple Regression Analysis
KW - Q&A Site
UR - https://www.scopus.com/pages/publications/85149844493
UR - https://www.scopus.com/pages/publications/85149844493#tab=citedBy
U2 - 10.1109/SNPD-Summer57817.2022.00031
DO - 10.1109/SNPD-Summer57817.2022.00031
M3 - Conference contribution
AN - SCOPUS:85149844493
T3 - Proceedings - 2022 23rd ACIS International Summer Virtual Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Summer 2022
SP - 134
EP - 140
BT - Proceedings - 2022 23rd ACIS International Summer Virtual Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Summer 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd ACIS International Summer Virtual Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Summer 2022
Y2 - 4 July 2022 through 6 July 2022
ER -