“语言数据科学与应用”系列学术讲座

为推动语言数据科学与应用学科的科学研究，展示语料库研究院科研团队的科研成果，进一步活跃研究院的科研氛围，上外语料库研究院自2022年10月起推出“语言数据科学与应用”系列学术讲座，每周举行一次（研究院有重大活动除外），第二期讲座将在2022年11月2日周三下午开始，敬请关注。

线上腾讯会议信息

主题：“语言数据科学与应用”系列学术讲座——Neutral or framed? A Big Data Sentiment Analysis of the portrayal of China in COVID-19 discourses

时间：2022年11月2日周三开始，下午3点（每周举行一次）

会议ID：383-2809-7780（周期性会议，每期会议号不变）

第二期 Muhammad Afzaal

Neutral or framed? A Big Data Sentiment Analysis of the portrayal of China in COVID-19 discourses

2022年11月2日，下午3点

主讲人：

Muhammad Afzaal，上海外国语大学语料库研究院副教授

主讲人简介：

Muhammad Afzaal joined the Institute of Corpus Studies and Applications, Shanghai International Studies University, China as an associate professor after gaining his PhD at the Shanghai Jiao Tong University, China and completing an extended research fellowship at the Hong Kong Polytechnic University, Hong Kong. His work experience also includes seven years of teaching in the undergrad and postgrad programs at Foundation University Islamabad, Pakistan. His PhD research comprised corpus-based analysis of discourses on the Belt and Road Initiative. He has received the Yang Yong research award from Shanghai Jiao Tong University's graduate school in China. Afzaal’s research interests include topics in the areas of corpus linguistics, discourse analysis, critical discourse analysis, translation studies and the integration of language sciences with NLP and big data. He is guest editor of his two special issues in Frontiers in Psychology,  Frontiers in Bid Data, and Frontiers in Artificial Intelligence. He has published extensively in SSCI, Scopus and ESCI Indexed International journals such as Critical Discourse Studies, Corpora, International Journal of Applied Linguistics, Discourse Studies, Asia Pacific Business Review, Critical Arts, Chinese Journal of Communication, Asian Journal of Communications, Frontiers in Psychology, Australian Review of Applied Linguistics and Asian Journal of Comparative Politics. He can be reached at afzaal@shisu.edu.cn. 

Google Scholar:

https://scholar.google.com/citations?user=QN9vjPoAAAAJ&hl=en

讲座题目：

Neutral or framed? A Big Data Sentiment Analysis of the portrayal of China in COVID-19 discourses

讲座概要：

Aimed at familiarizing corpus linguistics students and researchers with an understanding of what sentiment analysis is, how it is performed, and the contexts in which it might be applied, the present paper serves as an illuminative introduction to sentiment analysis as a methodological approach. Commencing with a definition of sentiment analysis and a delineation of the domains open to the application of the approach, the paper presents the findings of a methodologically innovative study which integrates sentiment analysis with corpus linguistics. The focus of the study is on investigating the portrayal of China in the Coronavirus Corpus (TCC) made up of 12 million words. In recent years, sentiment analysis has become an increasingly popular method for examining large datasets. Sentiment analysis is a form of Natural Language Processing (NLP) that employs the utilization of automation in order to derive affective markers (emotive language) from textual data. By analyzing these markers, the study reveals insights that can be used to determine ways in which the covid discourses are framed and to detect bias, if any, in the language of these discourses. The research makes use of three different types of general-purpose sentiment analyzers (Stanford Core NLP Sentiment Analysis, TextBlob, and VADER). A general-purpose sentiment analyzer is considered to be beneficial for doing research on the linguistic bias of social media. The study highlights three distinct ways in which the media frames political ideas. As a result, the way in which COVID discourses are presented holds further implications for how they may be perceived on many other fronts. The study flags the need for future work on developing context-specific sentiment analysis techniques for assessing data about health found online. This study makes a significant contribution by employing the multiple general-purpose sentiment analyzer as a technique to investigate the representation and depiction of China in the Coronavirus Corpus (TCC).

系列讲座预告

第三期：2022年11月9日 王斌华

第四期：2022年11月16日 Kim Kyung Hye

第五期：2022年11月23日 Gwendonila Jeanne C Bouvier

第六期：2022年11月30日 倪亦斌

第七期：2022年12月7日 李晶洁

第八期：2022年12月14日 雷蕾