FinLin

FinLin是一个新颖的金融领域多源实体级情感语料库，由爱尔兰国立高威大学数据分析洞察中心的Tobias Daudert创建。该数据集包含来自投资者报告、公司报告、新闻文章和StockTwits微博客的数据，涵盖汽车行业多个实体，时间跨度为3个月。FinLin通过情感得分和相关性得分进行标注，范围分别为[-1.0, 1.0]和[0.0, 1.0]，并包含用于情感分析的文本跨度，以提供对标注者推理的额外洞察。FinLin旨在通过提供一个新颖且公开可用的金融情感语料库来补充现有知识，并促进金融情感分析及其在行为科学中潜在应用的研究。

FinLin is a novel multi-source entity-level sentiment corpus in the financial domain, created by Tobias Daudert from the Data Analytics Insight Centre at the National University of Ireland, Galway. This corpus comprises data sourced from investor reports, corporate reports, news articles, and StockTwits microblog posts, covering multiple entities in the automotive industry with a time span of three months. FinLin is annotated with sentiment scores and relevance scores, ranging from [-1.0, 1.0] and [0.0, 1.0] respectively, and includes text spans for sentiment analysis to provide additional insights into the annotators' reasoning. FinLin aims to supplement existing knowledge by providing a novel and publicly available financial sentiment corpus, and to advance research on financial sentiment analysis and its potential applications in behavioral science.

搜集汇总

背景与挑战

背景概述

FinLin是一个多源实体级金融情感分析语料库，包含汽车行业相关的投资者报告、公司报告、新闻和社交媒体数据，标注了情感和相关性分数，并提供了情感标注的文本片段。该数据集旨在促进金融情感分析和行为科学的研究。