blocks|key|4135711|text|匹兹堡大学的Sentiment+Lexicon可能就是你想要的。这是一个大约有8000个单词的词典，带有积极/中性/负面的情绪。它在this+paper中有更详细的描述，并在通用公共许可证下发布。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|4135712|entityMap|0|LINK|mutability|MUTABLE|url|http://mpqa.cs.pitt.edu/|1|http://www.cs.pitt.edu/~wiebe/pubs/papers/emnlp05polarity.pdf^0|6|H|0|1U|A|1|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@$A|O|B|P|1|Q]|$A|R|B|S|1|T]]|C|$]]|$1|D|3|-4|5|6|7|U|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]|L|$5|G|H|I|C|$J|M]]]]

The <a href="http://mpqa.cs.pitt.edu" rel="noreferrer">Sentiment Lexicon</a>, at the University of Pittsburgh might be what you are after. It's a lexicon of about 8,000 words with positive/neutral/negative sentiment. It's described in more detail in <a href="http://www.cs.pitt.edu/~wiebe/pubs/papers/emnlp05polarity.pdf" rel="noreferrer">this paper</a> and released under the GPL.

blocks|key|2025750|text|我来得有点晚，我只想指出，字典对情感分析的贡献有限。一些带有情感的句子不包含任何“情感”词--例如，“读这本书”在书评中可能是积极的，而在影评中可能是消极的。同样，情感词“不可预测”在惊险小说中可能是积极的，但在描述丰田的刹车系统时可能是消极的。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2025751|还有更多的。|2025752|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|F|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|G|8|@]|9|@]|A|$]]|$1|D|3|-4|5|6|7|H|8|@]|9|@]|A|$]]]|E|$]]

Arriving a bit late I'll just note that dictionaries have a limited contribution for sentiment analysis. 
Some sentiment bearing sentences do not contain any "sentiment" word - e.g. "read the book" which could be positive in a book review while negative in a movie review. 
Similarly, the sentiment word "unpredictable" could be positive in the context of a thriller but negative when describing the breaks system of the Toyota. 

and there are many more...

blocks|key|5553383|text|情感分析(观点挖掘)词典|type|unstyled|depth|inlineStyleRanges|entityRanges|data|5553384|5553385|MPQA+Subjectivity+Lexicon|unordered-list-item|offset|length|5553386|Bing+Liu+and+Minqing+Hu+Sentiment+Lexicon|5553387|SentiWordNet+(包含在NLTK)|5553388|VADER+Sentiment+Lexicon|5553389|SenticNet|5553390|LIWC+(not+free)|5553391|Harvard+Inquirer|5553392|ANEW|5553393|中|5553394|5553395|来源：|style|BOLD|5553396|5553397|Keenformatics+-+Sentiment+Analysis+lexicons+and+datasets+(my+blog)|5553398|Hutto,+C.+J.,+and+Eric+Gilbert.+"Vader:+A+parsimonious+rule-based+model+for+sentiment+analysis+of+social+media+text."+Eighth+International+AAAI+Conference+on+Weblogs+and+Social+Media.+2014.|5553399|Sentiment+Symposium+Tutorial+by+Christopher+Potts|5553400|Personal+experience|5553401|5553402|entityMap|0|LINK|mutability|MUTABLE|url|http://mpqa.cs.pitt.edu/#subj_lexicon|1|http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#lexicon|2|http://sentiwordnet.isti.cnr.it/|3|http://www.nltk.org/|4|https://github.com/cjhutto/vaderSentiment/blob/master/vaderSentiment/vader_sentiment_lexicon.txt|5|http://sentic.net/|6|http://www.liwc.net/|7|http://www.wjh.harvard.edu/~inquirer|8|http://csea.phhp.ufl.edu/media/anewmessage.html|9|http://keenformatics.blogspot.co.uk/2015/07/sentiment-analysis-lexicons-and-datasets.html|10|http://comp.social.gatech.edu/papers/icwsm14.vader.hutto.pdf|11|http://sentiment.christopherpotts.net/lexicons.html^0|0|0|0|P|0|0|0|15|1|0|0|C|2|H|4|3|0|0|N|4|0|0|9|5|0|0|F|6|0|0|G|7|0|0|4|8|0|0|0|0|3|0|0|0|1K|9|0|0|59|A|0|0|1D|B|0|0|0^^$0|@$1|2|3|4|5|6|7|26|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|27|8|@]|9|@]|A|$]]|$1|C|3|D|5|E|7|28|8|@]|9|@$F|29|G|2A|1|2B]]|A|$]]|$1|H|3|I|5|E|7|2C|8|@]|9|@$F|2D|G|2E|1|2F]]|A|$]]|$1|J|3|K|5|E|7|2G|8|@]|9|@$F|2H|G|2I|1|2J]|$F|2K|G|2L|1|2M]]|A|$]]|$1|L|3|M|5|E|7|2N|8|@]|9|@$F|2O|G|2P|1|2Q]]|A|$]]|$1|N|3|O|5|E|7|2R|8|@]|9|@$F|2S|G|2T|1|2U]]|A|$]]|$1|P|3|Q|5|E|7|2V|8|@]|9|@$F|2W|G|2X|1|2Y]]|A|$]]|$1|R|3|S|5|E|7|2Z|8|@]|9|@$F|30|G|31|1|32]]|A|$]]|$1|T|3|U|5|E|7|33|8|@]|9|@$F|34|G|35|1|36]]|A|$]]|$1|V|3|W|5|6|7|37|8|@]|9|@]|A|$]]|$1|X|3|-4|5|6|7|38|8|@]|9|@]|A|$]]|$1|Y|3|Z|5|6|7|39|8|@$F|3A|G|3B|10|11]]|9|@]|A|$]]|$1|12|3|-4|5|6|7|3C|8|@]|9|@]|A|$]]|$1|13|3|14|5|E|7|3D|8|@]|9|@$F|3E|G|3F|1|3G]]|A|$]]|$1|15|3|16|5|E|7|3H|8|@]|9|@$F|3I|G|3J|1|3K]]|A|$]]|$1|17|3|18|5|E|7|3L|8|@]|9|@$F|3M|G|3N|1|3O]]|A|$]]|$1|19|3|1A|5|E|7|3P|8|@]|9|@]|A|$]]|$1|1B|3|-4|5|6|7|3Q|8|@]|9|@]|A|$]]|$1|1C|3|-4|5|6|7|3R|8|@]|9|@]|A|$]]]|1D|$1E|$5|1F|1G|1H|A|$1I|1J]]|1K|$5|1F|1G|1H|A|$1I|1L]]|1M|$5|1F|1G|1H|A|$1I|1N]]|1O|$5|1F|1G|1H|A|$1I|1P]]|1Q|$5|1F|1G|1H|A|$1I|1R]]|1S|$5|1F|1G|1H|A|$1I|1T]]|1U|$5|1F|1G|1H|A|$1I|1V]]|1W|$5|1F|1G|1H|A|$1I|1X]]|1Y|$5|1F|1G|1H|A|$1I|1Z]]|20|$5|1F|1G|1H|A|$1I|21]]|22|$5|1F|1G|1H|A|$1I|23]]|24|$5|1F|1G|1H|A|$1I|25]]]]

<h1>Sentiment Analysis (Opinion Mining) lexicons</h1>

<ul>
<li><a href="http://mpqa.cs.pitt.edu/#subj_lexicon" rel="noreferrer">MPQA Subjectivity Lexicon</a></li>
<li><a href="http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#lexicon" rel="noreferrer">Bing Liu and Minqing Hu Sentiment Lexicon</a></li>
<li><a href="http://sentiwordnet.isti.cnr.it" rel="noreferrer">SentiWordNet</a> (Included in <a href="http://www.nltk.org" rel="noreferrer">NLTK</a>)</li>
<li><a href="https://github.com/cjhutto/vaderSentiment/blob/master/vaderSentiment/vader_sentiment_lexicon.txt" rel="noreferrer">VADER Sentiment Lexicon</a></li>
<li><a href="http://sentic.net" rel="noreferrer">SenticNet</a></li>
<li><a href="http://www.liwc.net" rel="noreferrer">LIWC (not free)</a></li>
<li><a href="http://www.wjh.harvard.edu/~inquirer" rel="noreferrer">Harvard Inquirer</a></li>
<li><a href="http://csea.phhp.ufl.edu/media/anewmessage.html" rel="noreferrer">ANEW</a></li>
</ul>

<hr>

Sources:

<ul>
<li><a href="http://keenformatics.blogspot.co.uk/2015/07/sentiment-analysis-lexicons-and-datasets.html" rel="noreferrer">Keenformatics - Sentiment Analysis lexicons and datasets</a> (my blog)</li>
<li><a href="http://comp.social.gatech.edu/papers/icwsm14.vader.hutto.pdf" rel="noreferrer">Hutto, C. J., and Eric Gilbert. "Vader: A parsimonious rule-based model for sentiment analysis of social media text." Eighth International AAAI Conference on Weblogs and Social Media. 2014.</a></li>
<li><a href="http://sentiment.christopherpotts.net/lexicons.html" rel="noreferrer">Sentiment Symposium Tutorial by Christopher Potts</a></li>
<li>Personal experience</li>
</ul>

blocks|key|5553272|text|刘兵教授提供了一本约6800字的英语词典，您可以从以下链接下载：Opinion+Mining,+Sentiment+Analysis,+and+Opinion+Spam+Detection|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|5553273|entityMap|0|LINK|mutability|MUTABLE|url|http://www.cs.uic.edu/%257Eliub/FBS/sentiment-analysis.html#lexicon^0|W|1Q|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

Professor Bing Liu provide an English Lexicon of about 6800 word, you can download form this link:
<a href="http://www.cs.uic.edu/%7Eliub/FBS/sentiment-analysis.html#lexicon" rel="noreferrer">Opinion Mining, Sentiment Analysis, and Opinion Spam Detection</a>

blocks|key|1629637|text|This+paper+from+2002描述了一种算法，该算法仅使用两个单词作为种子集，就可以从文本样本中自动生成这样的字典。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1629638|entityMap|0|LINK|mutability|MUTABLE|url|http://nparc.cisti-icist.nrc-cnrc.gc.ca/npsi/ctrl?action=rtdoc&an=8914166^0|0|K|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

<a href="http://nparc.cisti-icist.nrc-cnrc.gc.ca/npsi/ctrl?action=rtdoc&amp;an=8914166" rel="noreferrer">This paper from 2002</a> describes an algorithm for deriving such a dictionary from text samples automatically, using only two words as a seed set.

blocks|key|2025880|text|你可以在这里找到AFINN，也可以动态创建它。例如，每当未知的%2Bve单词出现时，就用%2B1添加它。就像香蕉是新的%2Bve单词，出现两次后，它就会变成%2B2。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|2025881|当你想要更多的文章和数据时，你的字典会变得更强大！|2025882|entityMap|0|LINK|mutability|MUTABLE|url|https://github.com/uwescience/datasci_course_materials/blob/master/assignment1/AFINN-111.txt^0|8|5|0|0|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@$A|O|B|P|1|Q]]|C|$]]|$1|D|3|E|5|6|7|R|8|@]|9|@]|C|$]]|$1|F|3|-4|5|6|7|S|8|@]|9|@]|C|$]]]|G|$H|$5|I|J|K|C|$L|M]]]]

<a href="https://github.com/uwescience/datasci_course_materials/blob/master/assignment1/AFINN-111.txt" rel="nofollow">AFINN</a> you can find here and also create it dynamically. Like whenever unknown +ve word comes add it with +1. Like banana is new +ve word and appearing twice then it will become +2. 

As much articles and data you craws your dictionary would become stronger!

blocks|key|5553452|text|哈佛-IV词典目录http://www.wjh.harvard.edu/~inquirer/homecat.htm至少有两套现成的正面/负面定向词典。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|5553453|entityMap|0|LINK|mutability|MUTABLE|url|http://www.wjh.harvard.edu/~inquirer/homecat.htm^0|9|1C|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

The Harvard-IV dictionary directory <a href="http://www.wjh.harvard.edu/~inquirer/homecat.htm" rel="nofollow">http://www.wjh.harvard.edu/~inquirer/homecat.htm</a> has at least two sets of ready-to-use dictionaries for positive/negative orientation.

blocks|key|2025996|text|你可以使用维达情感词典|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2025997|from+nltk.sentiment.vader+import+SentimentIntensityAnalyzer

sentence='APPle+is+good+for+health'
sid+=+SentimentIntensityAnalyzer()
ss+=+sid.polarity_scores(sentence)++
print(ss)|code-block|syntax|javascript|2025998|它会给你句子的极性。|2025999|输出：|2026000|+{'compound':+0.4404,+'neu':+0.58,+'pos':+0.42,+'neg':+0.0}|2026001|entityMap^0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|O|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|P|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|Q|8|@]|9|@]|A|$]]|$1|I|3|J|5|6|7|R|8|@]|9|@]|A|$]]|$1|K|3|L|5|D|7|S|8|@]|9|@]|A|$E|F]]|$1|M|3|-4|5|6|7|T|8|@]|9|@]|A|$]]]|N|$]]

You can use vader sentiment lexicon

<pre><code>from nltk.sentiment.vader import SentimentIntensityAnalyzer

sentence='APPle is good for health'
sid = SentimentIntensityAnalyzer()
ss = sid.polarity_scores(sentence) 
print(ss)
</code></pre>

it will give you the polarity of sentence.

output:

<pre><code> {'compound': 0.4404, 'neu': 0.58, 'pos': 0.42, 'neg': 0.0}
</code></pre>

blocks|key|2026031|text|Sentiwords给出155,000个单词(以及它们的极性，即从非常负面到非常积极的分数在-1和1之间)。词典已在here中讨论|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|2026032|entityMap|0|LINK|mutability|MUTABLE|url|https://hlt-nlp.fbk.eu/technologies/sentiwords|1|https://www.youtube.com/watch?v=3Pzni2yfGUQ&feature=youtu.be#t=4m30s^0|0|A|0|1M|4|1|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@$A|O|B|P|1|Q]|$A|R|B|S|1|T]]|C|$]]|$1|D|3|-4|5|6|7|U|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]|L|$5|G|H|I|C|$J|M]]]]

<a href="https://hlt-nlp.fbk.eu/technologies/sentiwords" rel="nofollow noreferrer">Sentiwords</a> gives 155,000 words (and their polarity, that is, a score between -1 and 1 for very negative through to very positive). The lexicon is discussed <a href="https://www.youtube.com/watch?v=3Pzni2yfGUQ&amp;feature=youtu.be#t=4m30s" rel="nofollow noreferrer">here</a>

I was wondering if anybody knew where I could obtain dictionaries of positive and negative words. I'm looking into sentiment analysis and this is a crucial part of it.

Sentiment Analysis Dictionaries

我想知道有没有人知道我在哪里可以找到积极和消极的词的字典。我正在研究情绪分析，这是其中至关重要的一部分。

问情感分析词典
EN

回答 9

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问情感分析词典EN

回答 9

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问情感分析词典
EN