BriefGPT.xyz
Aug, 2013
加拿大NRC：构建推文情感分析的最新技术
NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets
HTML
PDF
Saif M. Mohammad, Svetlana Kiritchenko, Xiaodan Zhu
TL;DR
本文介绍如何使用基于SVM算法的两种分类器来检测消息（如推文和短信）的情感和词汇层面上的情感，并详细描述了使用各种表层形式、语义和情感特征进行实现。其中，基于词典的特征在所有特征中获得了5个F-score点的增益，两个系统都可以使用现有资源进行复制。
Abstract
In this paper, we describe how we created two state-of-the-art
svm classifiers
, one to detect the sentiment of messages such as tweets and SMS (
message-level task
) and one to detect the sentiment of a term within
→