Semi-supervised discriminant analysis SDA which uses a combination of multiple embedding graphs and kernel SDA KSDA are adopted in supervised speech emotion recognition.When the emotional factors of speech signal samp...Semi-supervised discriminant analysis SDA which uses a combination of multiple embedding graphs and kernel SDA KSDA are adopted in supervised speech emotion recognition.When the emotional factors of speech signal samples are preprocessed different categories of features including pitch zero-cross rate energy durance formant and Mel frequency cepstrum coefficient MFCC as well as their statistical parameters are extracted from the utterances of samples.In the dimensionality reduction stage before the feature vectors are sent into classifiers parameter-optimized SDA and KSDA are performed to reduce dimensionality.Experiments on the Berlin speech emotion database show that SDA for supervised speech emotion recognition outperforms some other state-of-the-art dimensionality reduction methods based on spectral graph learning such as linear discriminant analysis LDA locality preserving projections LPP marginal Fisher analysis MFA etc. when multi-class support vector machine SVM classifiers are used.Additionally KSDA can achieve better recognition performance based on kernelized data mapping compared with the above methods including SDA.展开更多
The skiing economy is a typical experience economy,so understanding the experience of ski tourists is essential to the development of the destination.To enrich the tourism experience research in the emerging ski marke...The skiing economy is a typical experience economy,so understanding the experience of ski tourists is essential to the development of the destination.To enrich the tourism experience research in the emerging ski market,this paper studies the 7118 online reviews of beginner skiers by selecting the main ski resorts in China as a case study.The content analysis method and sentiment analysis based on the domain lexicon and custom rules are combined to explore the perception characteristics of the beginners from the two aspects of experience dimension and experience satisfaction.Three main results were found.(1)The five main dimensions that affect the ski tourism experience of beginners are interaction perception,price perception,reputation perception,risk perception and functional perception.(2)For beginners,skiing is the primary purpose of tourism instead of being the critical factor of the positive reviews.They pay more attention to the pleasure produced by interpersonal interactions.(3)From 2014/2015 ski season to 2010/2021 ski season,the positive sentiment of beginners had no obvious change,while the negative sentiment showed a continuous downward trend,and the negative sentiment was mainly distributed among reviews on price,low temperature and service.This paper not only expands the research perspective of ski tourism,but also provides managerial inspiration for ski destinations interested in attracting beginners from the emerging ski markets.展开更多
基金The National Natural Science Foundation of China(No.61231002,61273266)the Ph.D.Programs Foundation of Ministry of Education of China(No.20110092130004)
文摘Semi-supervised discriminant analysis SDA which uses a combination of multiple embedding graphs and kernel SDA KSDA are adopted in supervised speech emotion recognition.When the emotional factors of speech signal samples are preprocessed different categories of features including pitch zero-cross rate energy durance formant and Mel frequency cepstrum coefficient MFCC as well as their statistical parameters are extracted from the utterances of samples.In the dimensionality reduction stage before the feature vectors are sent into classifiers parameter-optimized SDA and KSDA are performed to reduce dimensionality.Experiments on the Berlin speech emotion database show that SDA for supervised speech emotion recognition outperforms some other state-of-the-art dimensionality reduction methods based on spectral graph learning such as linear discriminant analysis LDA locality preserving projections LPP marginal Fisher analysis MFA etc. when multi-class support vector machine SVM classifiers are used.Additionally KSDA can achieve better recognition performance based on kernelized data mapping compared with the above methods including SDA.
基金The Fundamental Research Funds for the Central Universities(2019JBWB002)The Major Project of National Social Science Foundation of China(20ZDA067)The General Project of Humanities and Social Sciences Research of National Level(17BTY057).
文摘The skiing economy is a typical experience economy,so understanding the experience of ski tourists is essential to the development of the destination.To enrich the tourism experience research in the emerging ski market,this paper studies the 7118 online reviews of beginner skiers by selecting the main ski resorts in China as a case study.The content analysis method and sentiment analysis based on the domain lexicon and custom rules are combined to explore the perception characteristics of the beginners from the two aspects of experience dimension and experience satisfaction.Three main results were found.(1)The five main dimensions that affect the ski tourism experience of beginners are interaction perception,price perception,reputation perception,risk perception and functional perception.(2)For beginners,skiing is the primary purpose of tourism instead of being the critical factor of the positive reviews.They pay more attention to the pleasure produced by interpersonal interactions.(3)From 2014/2015 ski season to 2010/2021 ski season,the positive sentiment of beginners had no obvious change,while the negative sentiment showed a continuous downward trend,and the negative sentiment was mainly distributed among reviews on price,low temperature and service.This paper not only expands the research perspective of ski tourism,but also provides managerial inspiration for ski destinations interested in attracting beginners from the emerging ski markets.
