TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Sentiment Analysis on Web-Scraped Data

79 点作者 shrig94超过 10 年前

4 条评论

dingdingdang超过 10 年前
This is very interesting and well written article. Must admit that the fully online nature of the tools discourage rather than encourage in my case: why take the time to learn complexities of something as ephemeral as, what seems like, brand new web service? Especially when even large player like Google routinely retire whole platforms when they are not popular enough.<p>All the same, the tech itself seems solid and article is as mentioned superb so I&#x27;m really just beating the proverbial drum for proper distributed services here (or plain old offline capable apps).
评论 #8765563 未加载
Profan超过 10 年前
If you haven&#x27;t yet attempted to build some sort of sentiment analysis by yourself yet, be it rule-based or on statistical analysis, you should, even just a rudimentary rule based one is a lot of fun to implement, and it works surprisingly well [0].<p>One of the harder parts of making a decent one based on statistical analysis however is the lack of good training data, other than the analyzed twitter dataset [1] and another movie reviews one [2].<p>[0] <a href="http://fjavieralba.com/basic-sentiment-analysis-with-python.html" rel="nofollow">http:&#x2F;&#x2F;fjavieralba.com&#x2F;basic-sentiment-analysis-with-python....</a><p>[1] <a href="http://help.sentiment140.com/for-students/" rel="nofollow">http:&#x2F;&#x2F;help.sentiment140.com&#x2F;for-students&#x2F;</a><p>[2] <a href="http://www.cs.cornell.edu/people/pabo/movie-review-data/" rel="nofollow">http:&#x2F;&#x2F;www.cs.cornell.edu&#x2F;people&#x2F;pabo&#x2F;movie-review-data&#x2F;</a>
评论 #8765433 未加载
hnriot超过 10 年前
this is cool, but you can do the same with beautifulsoup and textblob in far fewer lines of code and you wouldn&#x27;t need any web services. if textblob isn&#x27;t your thing there&#x27;s plenty of svm implementations out there.<p>for more interesting sentiment analysis approaches check out sentence vectors, that&#x27;s the current bleeding edge of research in this area.<p>most sentiment analysis systems need to use an ensemble classifier because the domain of the text is very important. identifying the domain and using the appropriate domain specific model is important.
silentrob超过 10 年前
Very cool. MonkeyLearn looks promising. It would be nice if their docs were a little more clear around uploading CSV and the data structure.<p>It would also be cool if it did unsupervised learning.