谷歌自然语言情感分析总分 [英] Google Natural Language Sentiment Analysis Aggregate Scores

问题描述

在 Google Cloud Platform 文档的这一部分中Natural Language API，描述为

In this part of the documentation of the Google Cloud Platform Natural Language API, it is described that

实体的总分和量级值是实体每次提及的特定得分和量级值的总和.

我无法弄清楚这种聚合是如何工作的.在文档中提供的示例中，Marvin Gaye 有两次提及.其中一个提及的情绪为 0.4，震级为 0.4，另一个提及的得分为 -0.2，震级为 0.2.Marvin Gaye 的总体情绪得分为 0.1，震级为 0.6.

I can't figure out how this aggregation works. In the example provided in the documentation, Marvin Gaye has two mentions. One of the mentions has a sentiment of 0.4 and a magnitude of 0.4, the other mention has a score of -0.2 and a magnitude 0.2. The aggregate sentiment for Marvin Gaye is score 0.1 and magnitude 0.6.

我自己尝试过其他文本，但无法弄清楚聚合是如何进行的.有人知道吗?

I have tried other texts myself and can't figure out how the aggregation is made. Does anyone know?

推荐答案

我联系了 Google Cloud Platform 支持并得到了这个答案:

I contacted Google Cloud Platform Support and got this answer:

聚合的工作方式是将输入文本分解为更小的组件，通常是 ngram，这可能是文档谈论聚合的原因，但是，聚合不是简单的添加，不能将每个实体的单个情感值相加以获得总分."

因此似乎无法简单解释聚合是如何进行的.

So it doesn't seem possible to give a simple explanation of exactly how the aggregation is made.

这篇关于谷歌自然语言情感分析总分的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！