{"title":"Correlations Between Positive or Negative Utterances and Basic Acoustic Features of Voice: a Preliminary Analysis","authors":"Łukasz Stolarski","doi":"10.18778/1731-7533.20.2.03","DOIUrl":null,"url":null,"abstract":"The major aim of this paper is to establish possible correlations between continuous sentiment scores and four basic acoustic characteristics of voice. In order to achieve this objective, the text of “A Christmas Carol” by Charles Dickens was tokenized at the sentence level. Next, each of the resulting text units was assessed in terms of sentiment polarity and aligned with the corresponding fragment in an audiobook. The results indicate weak but statistically significant correlations between sentiment scores and three acoustic features: the mean F0, the standard deviation of F0 and the mean intensity. These findings may be useful in selecting optimal acoustic features for model training in multimodal sentiment analysis. Also, they are essential from a linguistic point of view and could be applied in studies on such language phenomena as irony.","PeriodicalId":38985,"journal":{"name":"Research in Language","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Research in Language","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18778/1731-7533.20.2.03","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Arts and Humanities","Score":null,"Total":0}
引用次数: 0
Abstract
The major aim of this paper is to establish possible correlations between continuous sentiment scores and four basic acoustic characteristics of voice. In order to achieve this objective, the text of “A Christmas Carol” by Charles Dickens was tokenized at the sentence level. Next, each of the resulting text units was assessed in terms of sentiment polarity and aligned with the corresponding fragment in an audiobook. The results indicate weak but statistically significant correlations between sentiment scores and three acoustic features: the mean F0, the standard deviation of F0 and the mean intensity. These findings may be useful in selecting optimal acoustic features for model training in multimodal sentiment analysis. Also, they are essential from a linguistic point of view and could be applied in studies on such language phenomena as irony.
期刊介绍:
Research in Language (RiL) is an international journal committed to publishing excellent studies in the area of linguistics and related disciplines focused on human communication. Language studies, as other scholarly disciplines, undergo two seemingly counteracting processes: the process of diversification of the field into narrow specialized domains and the process of convergence, strengthened by interdisciplinarity. It is the latter perspective that RiL editors invite for the journal, whose aim is to present language in its entirety, meshing traditional modular compartments, such as phonetics, phonology, morphology, syntax, semantics, and pragmatics, and offer a multidimensional perspective which exposes varied but relevant aspects of language, e.g. the cognitive, the psychological, the institutional aspect, as well as the social shaping of linguistic convention and creativity.