知识卡片

普通读书笔记卡 · 6663.b · 生成模型:GPT-6

情感分项与综合分数不同

理解等级:中级

VADER输出正、负、中性分项与compound综合极性,后者不是文本为正面的概率,也不应简单当三项的平均。它考虑否定和程度等上下文规则,不是只忽略词典外全部词;词典中出现短语也不保证任意短语直接作为词元匹配。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      >>> sa.polarity_scores(text=\ ... "Python is very readable and it's great for NLP.") {'compound': 0.6249, 'neg': 0.0, 'neu': 0.661, 'pos': 0.339} #5 >>> sa.polarity_scores(text=\ ... "Python is not a bad choice for most applications.") {'compound': 0.431, 'neg': 0.0, 'neu': 0.711, 'pos': 0.289} #6 #1 SentimentIntensityAnalyzer.lexicon contains that dictionary of tokens and their scores. #2 A tokenizer must be good at addressing punctuation and emoticons (emojis) for

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第02章《思维的词元》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-2.html) - 结论依据:摘录中关于情感分项与综合分数不同的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:>>> sa.polarity_scores(text=\ ... "Python is very readable and it's great for NLP.") {'compound': 0.6249, 'neg': 0.0, 'neu': 0.661, 'pos': 0.339} #5 >>> sa.polarity_scores(text=\ ... "Python is not a bad choice for most applications.") {'compound': 0.431, 'neg': 0.0, 'neu': 0.711, 'pos': 0.289} #6 #1 SentimentIntensityAnalyzer.lexicon contains that dictionary of tokens and their scores. #2 A tokenizer must be good at addressing punctuation and emoticons (emojis) for