En este estudio se profundizará en la nueva concepción semiótica que acuña Julia Kristeva, quien a través de términos como genotexto, fenotexto, connotación y denotación, consigue analizar lo no analizable, creando un método analítico único en el campo de la comunicación. En base a estos postulados se ahondará en el rol del observador, ya que es en su proceso perceptivo donde se forma el significado. El cine se desliga de la codificación clásica del lenguaje para identificarse con la palabra poética, asentándose sobre la intertextualidad de códigos y nutriéndose de otros textos culturales previos. Por este motivo, trataremos toda expresión artística como un tejido de significados, influidos por el bagaje cultural y social tanto del emisor, como del receptor y del observador. Dado que contamos con una escasa metodología al servicio de este tipo de análisis, se finalizará el artículo con una propuesta basada en los postulados teóricos estudiados y aplicada a un caso práctico concreto, donde se clarificará cómo descomponer un filme para, posteriormente, examinar cada una de sus partes en términos comunicacionales.
{"title":"Hacia una nueva perspectiva semiótica y su aplicación al análisis fílmico: propuesta metodológica a partir de un caso práctico","authors":"Paula Grueso Pascual","doi":"10.35951/v2i2.85","DOIUrl":"https://doi.org/10.35951/v2i2.85","url":null,"abstract":"En este estudio se profundizará en la nueva concepción semiótica que acuña Julia Kristeva, quien a través de términos como genotexto, fenotexto, connotación y denotación, consigue analizar lo no analizable, creando un método analítico único en el campo de la comunicación. En base a estos postulados se ahondará en el rol del observador, ya que es en su proceso perceptivo donde se forma el significado. El cine se desliga de la codificación clásica del lenguaje para identificarse con la palabra poética, asentándose sobre la intertextualidad de códigos y nutriéndose de otros textos culturales previos. Por este motivo, trataremos toda expresión artística como un tejido de significados, influidos por el bagaje cultural y social tanto del emisor, como del receptor y del observador. Dado que contamos con una escasa metodología al servicio de este tipo de análisis, se finalizará el artículo con una propuesta basada en los postulados teóricos estudiados y aplicada a un caso práctico concreto, donde se clarificará cómo descomponer un filme para, posteriormente, examinar cada una de sus partes en términos comunicacionales.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84769530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
El método de análisis de textos literarios propuesto por Mikhail Bakhtin puede utilizarse también para el análisis de contenido en los medios de comunicación y ayuda a comparar y analizar científicamente las narraciones de los medios de comunicación sobre un tema específico en diferentes medios, idiomas y países. Las citas utilizadas en los medios de comunicación a menudo difieren de la fuente original de información. Estos errores suelen entonces señalarse como el resultado de una interpretación deliberadamente distorsionada o como noticias falsas. Para evitar esas discrepancias es aconsejable utilizar la teoría dialógica de Bakhtin, que propone el respeto de la "opinión ajena" cuando un periodista hace referencia a una información y la utiliza en el contenido de su relato. La ventaja de la heteroglosia es que permite observar cualquier cambio en el mismo texto después de que se haya publicado en los medios de comunicación de varios países. La autora rastrea aquí los aspectos que conciernen a la generación e interpretación de 890 artículos periodísticos.
{"title":"Notas sobre el uso del dialogismo (heteroglosia) de Mikhail Bakhtin como método de análisis de textos de medios de comunicación","authors":"","doi":"10.35951/v2i2.95","DOIUrl":"https://doi.org/10.35951/v2i2.95","url":null,"abstract":"El método de análisis de textos literarios propuesto por Mikhail Bakhtin puede utilizarse también para el análisis de contenido en los medios de comunicación y ayuda a comparar y analizar científicamente las narraciones de los medios de comunicación sobre un tema específico en diferentes medios, idiomas y países. Las citas utilizadas en los medios de comunicación a menudo difieren de la fuente original de información. Estos errores suelen entonces señalarse como el resultado de una interpretación deliberadamente distorsionada o como noticias falsas. Para evitar esas discrepancias es aconsejable utilizar la teoría dialógica de Bakhtin, que propone el respeto de la \"opinión ajena\" cuando un periodista hace referencia a una información y la utiliza en el contenido de su relato. La ventaja de la heteroglosia es que permite observar cualquier cambio en el mismo texto después de que se haya publicado en los medios de comunicación de varios países. La autora rastrea aquí los aspectos que conciernen a la generación e interpretación de 890 artículos periodísticos.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78610049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A workshop for communication research","authors":"","doi":"10.35951/v2i2","DOIUrl":"https://doi.org/10.35951/v2i2","url":null,"abstract":"","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88786762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Enzo Rainiero Ferrari Lagos, Fernando Martínez Abad, Camilo Ruiz Méndez
El Cambio Climático (CC) es la mayor amenaza para nuestra sociedad, pero, aunque la ciencia presenta evidencias claras sobre la magnitud del problema y describe con precisión las consecuencias, las personas no están actuando lo suficiente. La razón detrás de esta paradoja podría ser la no apropiada Representación Social (RS) sobre el CC en la sociedad y puede explicar por qué todavía existen creencias escépticas y negacionistas, así como su no adecuada comunicación. Mediante un diseño cuasi experimental con pretest y postest se verifica si los MOOC´s bien diseñados y basados en evidencia científica pueden mejorar la RS del CC, generando conciencia y una movilización efectiva para abordar este importante tema.
{"title":"La eficiencia de un MOOC de Ciencia básica en español para mejorar la representación social del Cambio Climático","authors":"Enzo Rainiero Ferrari Lagos, Fernando Martínez Abad, Camilo Ruiz Méndez","doi":"10.35951/v2i2.81","DOIUrl":"https://doi.org/10.35951/v2i2.81","url":null,"abstract":"El Cambio Climático (CC) es la mayor amenaza para nuestra sociedad, pero, aunque la ciencia presenta evidencias claras sobre la magnitud del problema y describe con precisión las consecuencias, las personas no están actuando lo suficiente. La razón detrás de esta paradoja podría ser la no apropiada Representación Social (RS) sobre el CC en la sociedad y puede explicar por qué todavía existen creencias escépticas y negacionistas, así como su no adecuada comunicación. Mediante un diseño cuasi experimental con pretest y postest se verifica si los MOOC´s bien diseñados y basados en evidencia científica pueden mejorar la RS del CC, generando conciencia y una movilización efectiva para abordar este importante tema.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83546476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-12DOI: 10.1080/19312458.2020.1846695
K. Fujiwara, Quinten S. Bernhold, Norah E. Dunbar, Christopher D. Otmar, Mohemmad Hansia
ABSTRACT The manual coding of nonverbal cues by trained human coders, such as counting the occurrence of a specific behavior or subjective rating about a speaker, is still a major method in the study of nonverbal synchrony. However, its time-consuming nature has been a serious barrier to the development of the field and has made it difficult for new scholars to adopt the technique. Recent advances in automated coding techniques allow researchers to collect nonverbal behavioral data effectively and objectively, but it is unclear how comparable the manual and automated coding methods are. This study, therefore, directly compared both methods of coding in a face-to-face conversation experiment. In the manual coding, a software system C-BAS was employed to count the occurrence of synchrony in gesture, posture, nodding, and other cues. In the automated coding, a cross-correlation analysis and a cross-wavelet coherence analysis were separately performed for the participant’s movement data. The results showed that the manual and automated coding were moderately correlated, and yielded similar significant differences between experimental conditions of conversational involvement in the degree of synchrony. Further, synchrony measured via both coding techniques was significantly associated with post-conversation self-reports. The advantages and disadvantages of both techniques are discussed.
{"title":"Comparing Manual and Automated Coding Methods of Nonverbal Synchrony","authors":"K. Fujiwara, Quinten S. Bernhold, Norah E. Dunbar, Christopher D. Otmar, Mohemmad Hansia","doi":"10.1080/19312458.2020.1846695","DOIUrl":"https://doi.org/10.1080/19312458.2020.1846695","url":null,"abstract":"ABSTRACT The manual coding of nonverbal cues by trained human coders, such as counting the occurrence of a specific behavior or subjective rating about a speaker, is still a major method in the study of nonverbal synchrony. However, its time-consuming nature has been a serious barrier to the development of the field and has made it difficult for new scholars to adopt the technique. Recent advances in automated coding techniques allow researchers to collect nonverbal behavioral data effectively and objectively, but it is unclear how comparable the manual and automated coding methods are. This study, therefore, directly compared both methods of coding in a face-to-face conversation experiment. In the manual coding, a software system C-BAS was employed to count the occurrence of synchrony in gesture, posture, nodding, and other cues. In the automated coding, a cross-correlation analysis and a cross-wavelet coherence analysis were separately performed for the participant’s movement data. The results showed that the manual and automated coding were moderately correlated, and yielded similar significant differences between experimental conditions of conversational involvement in the degree of synchrony. Further, synchrony measured via both coding techniques was significantly associated with post-conversation self-reports. The advantages and disadvantages of both techniques are discussed.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19312458.2020.1846695","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46627742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
El objetivo de este artículo es exponer el planteamiento metodológico para desarrollar un estudio neurocinemático del cambio de plano por corte. Concretamente, el estudio se realiza mediante el análisis del event-related desynchronization/synchronization del electroencefalograma registrado sobre espectadores. Se parte desde una perspectiva general describiendo las implicaciones de aplicar las metodologías neurocinemáticas al análisis fílmico, para finalizar con la peculiaridades que implica nuestra investigación. En nuestro caso trabajamos a partir de fragmentos cinematográficos extraídos de largometrajes ya existentes, realizamos un registro neuronal con 31 electrodos y aplicamos un análisis estadístico basado en el test de permutaciones, el test de correlación de Spearman y el análisis de pendientes sobre la señal registrada transformada al dominio de la frecuencia.
{"title":"Metodología para el estudio neurocinemático del cambio de plano por corte a través del electroencefalograma","authors":"Javier Sanz Aznar, L. Gómez, Luis Emilio Bruni","doi":"10.35951/v2i2.82","DOIUrl":"https://doi.org/10.35951/v2i2.82","url":null,"abstract":"El objetivo de este artículo es exponer el planteamiento metodológico para desarrollar un estudio neurocinemático del cambio de plano por corte. Concretamente, el estudio se realiza mediante el análisis del event-related desynchronization/synchronization del electroencefalograma registrado sobre espectadores. Se parte desde una perspectiva general describiendo las implicaciones de aplicar las metodologías neurocinemáticas al análisis fílmico, para finalizar con la peculiaridades que implica nuestra investigación. En nuestro caso trabajamos a partir de fragmentos cinematográficos extraídos de largometrajes ya existentes, realizamos un registro neuronal con 31 electrodos y aplicamos un análisis estadístico basado en el test de permutaciones, el test de correlación de Spearman y el análisis de pendientes sobre la señal registrada transformada al dominio de la frecuencia.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84608760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ABSTRACT The increasing adoption of brain imaging methods has greatly augmented our understanding of the neural underpinnings of communication processes. Enabled by recent advancements in mathematics and computational infrastructure, researchers have begun to move beyond traditional univariate analytic techniques in favor of methods that consider the brain in terms of evolving networks of interactions between brain regions. This network neuroscience approach is a potential boon to communication and media psychology research but also requires a careful look at the complications inherent in adopting a novel (and complex) methodological tool. In this manuscript, we provide an overview of network neuroscience in view of the needs of communication neuroscientists, discussing considerations that must be taken into account when constructing networks from neuroimaging data and conducting statistical tests on these networks. Throughout the manuscript, we highlight research domains in which network neuroscience is likely to be particularly useful for increasing theoretical clarity in communication and media psychology research.
{"title":"A Practical Introduction to Network Neuroscience for Communication Researchers","authors":"J. T. Fisher, F. R. Hopp, R. Weber","doi":"10.31219/osf.io/4txuf","DOIUrl":"https://doi.org/10.31219/osf.io/4txuf","url":null,"abstract":"ABSTRACT The increasing adoption of brain imaging methods has greatly augmented our understanding of the neural underpinnings of communication processes. Enabled by recent advancements in mathematics and computational infrastructure, researchers have begun to move beyond traditional univariate analytic techniques in favor of methods that consider the brain in terms of evolving networks of interactions between brain regions. This network neuroscience approach is a potential boon to communication and media psychology research but also requires a careful look at the complications inherent in adopting a novel (and complex) methodological tool. In this manuscript, we provide an overview of network neuroscience in view of the needs of communication neuroscientists, discussing considerations that must be taken into account when constructing networks from neuroimaging data and conducting statistical tests on these networks. Throughout the manuscript, we highlight research domains in which network neuroscience is likely to be particularly useful for increasing theoretical clarity in communication and media psychology research.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44273572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1080/19312458.2020.1832976
Kohei Watanabe
ABSTRACT Many social scientists recognize that quantitative text analysis is a useful research methodology, but its application is still concentrated in documents written in European languages, especially English, and few sub-fields of political science, such as comparative politics and legislative studies. This seems to be due to the absence of flexible and cost-efficient methods that can be used to analyze documents in different domains and languages. Aiming to solve this problem, this paper proposes a semisupervised document scaling technique, called Latent Semantic Scaling (LSS), which can locate documents on various pre-defined dimensions. LSS achieves this by combining user-provided seed words and latent semantic analysis (word embedding). The article demonstrates its flexibility and efficiency in large-scale sentiment analysis of New York Times articles on the economy and Asahi Shimbun articles on politics. These examples show that LSS can produce results comparable to that of the Lexicoder Sentiment Dictionary (LSD) in both English and Japanese with only small sets of sentiment seed words. A new heuristic method that assists LSS users to choose a near-optimal number of singular values to obtain word vectors that best capture differences between documents on target dimensions is also presented.
{"title":"Latent Semantic Scaling: A Semisupervised Text Analysis Technique for New Domains and Languages","authors":"Kohei Watanabe","doi":"10.1080/19312458.2020.1832976","DOIUrl":"https://doi.org/10.1080/19312458.2020.1832976","url":null,"abstract":"ABSTRACT Many social scientists recognize that quantitative text analysis is a useful research methodology, but its application is still concentrated in documents written in European languages, especially English, and few sub-fields of political science, such as comparative politics and legislative studies. This seems to be due to the absence of flexible and cost-efficient methods that can be used to analyze documents in different domains and languages. Aiming to solve this problem, this paper proposes a semisupervised document scaling technique, called Latent Semantic Scaling (LSS), which can locate documents on various pre-defined dimensions. LSS achieves this by combining user-provided seed words and latent semantic analysis (word embedding). The article demonstrates its flexibility and efficiency in large-scale sentiment analysis of New York Times articles on the economy and Asahi Shimbun articles on politics. These examples show that LSS can produce results comparable to that of the Lexicoder Sentiment Dictionary (LSD) in both English and Japanese with only small sets of sentiment seed words. A new heuristic method that assists LSS users to choose a near-optimal number of singular values to obtain word vectors that best capture differences between documents on target dimensions is also presented.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19312458.2020.1832976","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42117466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-01DOI: 10.1080/19312458.2020.1825659
Eran Amsalem, Yair Fogel-Dror, Shaul R. Shenhav, Tamir Sheafer
ABSTRACT Many researchers consider the presentation of diverse content as a prerequisite for the news media to fully exercise their democratic mandate. While prior news diversity studies have contributed important theoretical insights, we argue here that scholarly knowledge of this concept can be significantly advanced by employing computational methods for text analysis. Using automated methods, researchers can increase both the scope of data being analyzed and the resolution of the analysis. This article presents a novel framework for analyzing news diversity consisting of two distinct stages. In the first stage, a computational text classification method is used to analyze, at a high resolution, the attention given in news texts to a broad range of political and social issues. In the second stage, the text classifications are aggregated, and the distributions of media attention to those issues (i.e., news diversity) are assessed on a large scale. After presenting the novel approach, we illustrate its usefulness for testing theoretical hypotheses about news diversity. We compare the diversity of economic coverage in three elite and three popular US newspapers (N = 252,807 articles) and find that a fine-grained analysis relaxes concerns raised in previous studies about low content diversity in the popular press.
{"title":"Fine-Grained Analysis of Diversity Levels in the News","authors":"Eran Amsalem, Yair Fogel-Dror, Shaul R. Shenhav, Tamir Sheafer","doi":"10.1080/19312458.2020.1825659","DOIUrl":"https://doi.org/10.1080/19312458.2020.1825659","url":null,"abstract":"ABSTRACT Many researchers consider the presentation of diverse content as a prerequisite for the news media to fully exercise their democratic mandate. While prior news diversity studies have contributed important theoretical insights, we argue here that scholarly knowledge of this concept can be significantly advanced by employing computational methods for text analysis. Using automated methods, researchers can increase both the scope of data being analyzed and the resolution of the analysis. This article presents a novel framework for analyzing news diversity consisting of two distinct stages. In the first stage, a computational text classification method is used to analyze, at a high resolution, the attention given in news texts to a broad range of political and social issues. In the second stage, the text classifications are aggregated, and the distributions of media attention to those issues (i.e., news diversity) are assessed on a large scale. After presenting the novel approach, we illustrate its usefulness for testing theoretical hypotheses about news diversity. We compare the diversity of economic coverage in three elite and three popular US newspapers (N = 252,807 articles) and find that a fine-grained analysis relaxes concerns raised in previous studies about low content diversity in the popular press.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19312458.2020.1825659","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41525351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-07DOI: 10.1080/19312458.2020.1812555
Chung-hong Chan, Jing Zeng, Hartmut Wessler, Marc Jungblut, Kasper Welbers, Joseph W. Bajjalieh, Wouter van Atteveldt, Scott L. Althaus
ABSTRACT With global media content databases and online content being available, analyzing topical structures in different languages simultaneously has become an urgent computational task. Some previous studies have analyzed topics in a multilingual corpus by translating all items into a single language using a machine translation service, such as Google Translate. We argue that this method is not reproducible in the long run and proposes a new method – Reproducible Extraction of Cross-lingual Topics Using R (rectr). Our method utilizes open-source-aligned word embeddings to understand the cross-lingual meanings of words and has a mechanism to normalize residual influence from language differences. We present a benchmark that compares the topics extracted from a corpus of English, German, and French news using our method with methods used in the literature. We show that our method is not only reproducible but can also generate high-quality cross-lingual topics. We demonstrate how our method can be applied in tracking news topics across time and languages.
{"title":"Reproducible Extraction of Cross-lingual Topics (rectr)","authors":"Chung-hong Chan, Jing Zeng, Hartmut Wessler, Marc Jungblut, Kasper Welbers, Joseph W. Bajjalieh, Wouter van Atteveldt, Scott L. Althaus","doi":"10.1080/19312458.2020.1812555","DOIUrl":"https://doi.org/10.1080/19312458.2020.1812555","url":null,"abstract":"ABSTRACT With global media content databases and online content being available, analyzing topical structures in different languages simultaneously has become an urgent computational task. Some previous studies have analyzed topics in a multilingual corpus by translating all items into a single language using a machine translation service, such as Google Translate. We argue that this method is not reproducible in the long run and proposes a new method – Reproducible Extraction of Cross-lingual Topics Using R (rectr). Our method utilizes open-source-aligned word embeddings to understand the cross-lingual meanings of words and has a mechanism to normalize residual influence from language differences. We present a benchmark that compares the topics extracted from a corpus of English, German, and French news using our method with methods used in the literature. We show that our method is not only reproducible but can also generate high-quality cross-lingual topics. We demonstrate how our method can be applied in tracking news topics across time and languages.","PeriodicalId":47552,"journal":{"name":"Communication Methods and Measures","volume":null,"pages":null},"PeriodicalIF":11.4,"publicationDate":"2020-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/19312458.2020.1812555","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47916183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：