相关实验视频

Updated: Jun 3, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

为话语研究部署大型语言模型:对媒体态度的自动化分析的探索

Qingyu Gao¹, Dezheng William Feng¹

¹Department of English and Communication, The Hong Kong Polytechnic University, Kowloon, Hong Kong SAR, China.

|January 9, 2025

概括

本研究引入了一种大型语言模型 (LLM) 方法,用于分析香港报纸中媒体对中国的态度. 该法学士准确地识别了明确和隐含的态度,在个人电脑上实现了80%的成功率.

科学领域:

计算语言学计算语言学
媒体研究媒体研究
自然语言处理自然语言处理.

背景情况:

分析媒体态度对于理解论和社会动态至关重要.
基于语料库的传统方法往往忽略了隐含的态度表达.
大型语言模型 (LLM) 为全面的态度分析提供了潜力.

研究的目的:

开发和评估基于LLM的方法,用于对媒体态度的话语分析.
用这种方法调查香港报纸对中国的媒体态度.
评估在个人电脑上部署LLM用于态度分析的可行性.

主要方法:

使用了Meta的开源Llama2 (13b) 模型,用于个人电脑部署.
应用了马丁和怀特的框架来描述态度.
分析了香港报纸东方每日新闻中关于中国的4万个表达式.

主要成果:

量子化的LLM成功地确定了对中国的明确和隐含态度.
实现了大约80%的准确率,与人类编码器相当.
证明了用于媒体态度分析的本地LLM部署的可行性.

结论:

基于LLM的话语分析对于捕捉微妙的媒体态度是有效的.
量子化LLM为标准硬件研究人员提供了可行的和准确的工具.
进一步的研究可以探索在媒体研究中LLM实施的挑战和策略.

更多相关视频

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

相关概念视频

Stereotype Content Model

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...

Language and Cognition

Language and Cognition

Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.