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。

Ask HN: Would you use a review sentiment search engine?

2 点作者 dopplesoldner大约 11 年前
Hi guys, wanted to get some opinion about an idea I&#x27;ve had. Constructive and honest feedback will be really appreciated.<p>A sentiment search engine. Suppose you type the name of a restaurant&#x2F;camera&#x2F;hotels&#x2F;protein supplement etc. - you will get a condensed graphical view of with &quot;sentiment scores&quot; in different categories based on what real customers have been saying around the internet. E.g for an iphone, entities might be battery, display etc.<p>Data is scraped from individual reviews, shopping sites etc. Additionally you get information about the original source of information so you can carry further research if you want to.<p>So in short, it can be the default go to place for any kind of reviews.

4 条评论

neuralk大约 11 年前
This is a great idea. I would use it. In fact, I want to build it! I&#x27;ve been reading about sentiment analysis as part of my research, and I had this idea literally the other day: I was looking for laptop batteries and I did not have the patience to search through some N number of Amazon&#x2F;eBay&#x2F;other storefronts. The second issue was the fact reviews range from 1 star to 5 star on the same product BUT a crucial fact was that more recent reviews are more relevant (for instance, if everyone from the past 3 months is rating it 1 star, vs. only 5 star where all previous bad reviews were from 3+ years ago).<p>So how would you define sentiment? A single score on a range from &quot;good&quot; to &quot;bad&quot;? Multidimensional, like a range of emotions? A major problem I&#x27;ve found in sentiment analysis literature that some assumptions&#x2F;models yield limited&#x2F;poor results even if algorithms are good.<p>Have you started working on this? I&#x27;d be happy to discuss it or your ideas some more.
评论 #7553247 未加载
ohashi大约 11 年前
This sounds very similar to what I do for web hosting reviews. For instance, take a look at Digital Ocean&#x27;s reviews: <a href="http://reviewsignal.com/webhosting/company/101/digitalocean/" rel="nofollow">http:&#x2F;&#x2F;reviewsignal.com&#x2F;webhosting&#x2F;company&#x2F;101&#x2F;digitalocean&#x2F;</a><p>It calculates an overall (based on all pos&#x2F;neg things said) but breaks down into components relevant to web hosting: support, uptime, price. You can also figure out who competitors are and see trends.<p>If you can&#x27;t tell, I like the idea. I also think it&#x27;s an incredibly hard problem to solve. I&#x27;ve done it for a small niche. Scaling it to a general solution is something I haven&#x27;t been able to figure out (yet).
nateday大约 11 年前
I agree with @manmeet that the algorithm for the sentiment analysis has to be great; the search algorithm also has to be tremendous to convince me to switch from Google or DuckDuckGo. To avoid the challenge of making a new search engine, maybe you could build a plugin?<p>Somewhat similar sentiment analysis, for terms rather than unique entities: <a href="http://www.whatdoestheinternetthink.net" rel="nofollow">http:&#x2F;&#x2F;www.whatdoestheinternetthink.net</a>
评论 #7549079 未加载
manmeet大约 11 年前
I think its a pretty good idea. All depends on how well u design your algorithm. I had a similar idea but wanted to use twitter to get sentiment regarding anything, from people to movies to devices or services.