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。

Launch HN: Thematic (YC S17) Customer Feedback Analysis via NLP

72 点作者 zelandiya将近 8 年前
Hi! I’m the CEO of Thematic, <a href="http:&#x2F;&#x2F;www.getthematic.com" rel="nofollow">http:&#x2F;&#x2F;www.getthematic.com</a>. We analyse customer feedback to tell companies how to increase customer satisfaction and reduce churn.<p>We are one of the handful of companies that got into YC through the Startup School, and (I have to say) the only company that signed YC itself as a customer!<p>I have a PhD in NLP and ML and was consulting when two large media companies came to me with a problem: They collect tons of customer feedback in free text as part of their NPS surveys, but don’t have the time to sift through the responses.<p>This turned out to be common. Most companies collect feedback but, especially in large companies, nobody reads this data, and definitely not people who are in charge of strategy. Customers are screaming what’s wrong and what they want, but nobody is listening.<p>I tried a few open-source packages but found that none worked well. Developed on canonical text like news article or Wikipedia, they either failed to understand the variety of expressions, or were too hard to explain. I wrote a new approach capitalising on my PhD and new Deep Learning approaches. It&#x27;s completely unsupervised: just needs raw data but, unlike topic modelling, produces clear and specific themes. My husband Nathan joined as a co-founder and for the next year we learned how to solve this problem in a way customer insights professionals find valuable.<p>Those media companies became customers and we quickly bootstrapped into a profitable startup. This is when Nathan signed up for YC’s Startup School. We grew 20% in those 10 weeks, loved the accountability and the focus. Our mentor suggested we apply for YC, which seemed like a crazy idea, but we gave it a go.<p>Fast-forward another 2 months, and we are just before Demo Day! Thematic grew 3x in that time, and we are working with brands like Vodafone, Air New Zealand, Stripe, Ableton, and Manpower Group.<p>Hope you found our story interesting, and happy to answer any questions.

14 条评论

textient将近 8 年前
Suggestions to your business growth:<p>Surveys are the bread and butter for many market research companies. Most of the corporates &#x2F; enterprises typically engage with smaller to larger (and many a times multiple) MR agencies. These MR companies can benefit from your service. To explore these companies, you can check out the MR members directory list from ESOMAR ,the voice of the MR (www.esomar.org), perhaps a membership &#x2F; participating in their events may help you. Other site is agencyspotter.com<p>Explore publishing an article at the Greenbook blog run by Leonard Murphy which is very relevant to this case and he also runs the IIEX events globally ( <a href="http:&#x2F;&#x2F;iiex-na.insightinnovation.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;iiex-na.insightinnovation.org&#x2F;</a> ) where tools &#x2F;services such as yours are very much the hot thing..<p>Check out Unilever Foundry <a href="https:&#x2F;&#x2F;foundry.unilever.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;foundry.unilever.com&#x2F;</a> . You can sign up and explore if you can help solve some of their problems with your solution. They select and fund Pilot projects<p>Twitter hashtags to get your tool noted in the MR industry #mrx #newmr<p>Ads &#x2F; promotions: check out <a href="http:&#x2F;&#x2F;newmr.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;newmr.org&#x2F;</a> , <a href="http:&#x2F;&#x2F;www.greenbookblog.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.greenbookblog.org&#x2F;</a><p>Explore if you have complementary business synergies to present with <a href="https:&#x2F;&#x2F;www.zappistore.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.zappistore.com&#x2F;</a> (e.g your product could be a part of the Zappistore platform as an App.)<p>Best Wishes, N.Sankar <a href="https:&#x2F;&#x2F;www.linkedin.com&#x2F;in&#x2F;nsk007" rel="nofollow">https:&#x2F;&#x2F;www.linkedin.com&#x2F;in&#x2F;nsk007</a>
评论 #15027625 未加载
wadkar将近 8 年前
Congratulations and best wishes!<p>I for one really liked the demo and the blog - specifically, (a) I have great exemplars for what you mean by &quot;theme&quot;, and (b) this post[1] shows great insights into your thinking about the problem faced by your customers<p>&gt; Developed on canonical text like news article or Wikipedia, they either failed to understand the variety of expressions, or were too hard to explain.<p>It appears to me that the current methods and resulting tools are heavily dependent on the problem formulation (or domain in general). Moreover, no matter how fancy your technique is (or &quot;how deep is your net&quot;), the resulting model won&#x27;t work unless you take specific steps to train it on data from the domain.<p>Yes, what I just said sounds borderline truism. However, I am more interested in discussing why it is so? Here&#x27;s my initial thinking:<p>Let us look at (one of) the definition of Machine Learning, from Prof Tom Mitchell&#x27;s textbook, &quot;A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.&quot;<p>Here, experience E can be loosely considered as the amount of data you have for training - obviously, more data (i.e. training) should improve learning. However, the abstraction of T and P hides an important underlying problem of specification - or in other words, formulation of T (and E).<p>Thoughts?<p>&gt; I wrote a new approach [capitalizing] on my PhD and new Deep Learning approaches.<p>I hope we get to see some of your insights in a paper or article (or blog post :)<p>[1] <a href="https:&#x2F;&#x2F;www.getthematic.com&#x2F;post&#x2F;visualizing-customer-feedback-three-alternatives-word-clouds&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.getthematic.com&#x2F;post&#x2F;visualizing-customer-feedba...</a>
评论 #15022812 未加载
randoman将近 8 年前
I really enjoyed reading about your company on Idealog (<a href="https:&#x2F;&#x2F;idealog.co.nz&#x2F;technologymonth&#x2F;2017&#x2F;08&#x2F;meet-thematic-new-zealand-startup-making-waves-y-combinator" rel="nofollow">https:&#x2F;&#x2F;idealog.co.nz&#x2F;technologymonth&#x2F;2017&#x2F;08&#x2F;meet-thematic-...</a>). It was especially great to see how you bootstrapped and found product-market fit rather than just raising a bunch of cash for an idea that may or may not be applicable in the real world. Congratulations on the launch and your success with YC. Go Kiwis!
评论 #15024790 未加载
tixocloud将近 8 年前
Congratulations on your launch! This is very interesting and it&#x27;s something that has great applicability. Being in financial services, we collect a ton of feedback and audio but not enough manpower to process it all. I love the themed approach but am curious about the subthemes. Would you be able to shed any light on that?<p>I&#x27;m also happy to make introductions if you&#x27;re ever thinking about expanding up north to Canada.
评论 #15021173 未加载
jstandard将近 8 年前
Great tool, this is an area I&#x27;ve been looking forward to more automation in.<p>I might have missed it on the website, how does pricing work?<p>Also, do you have any integrations with other tools like Intercom or Zendesk to ease data-sharing? A monthly insights report generated directly off of my main customer support tool can replace hours of manual work.
评论 #15023828 未加载
Yertis将近 8 年前
Love this! When I was at one of the big tech companies years ago, we tried to do something like this for reviews for all the products, and see how they stacked up in the marketplace. Was a really challenging problem to do in an automated way at scale -- definitely wish we had a solution like this!<p>Do you guys see yourselves sticking to a model that spits out analysis, and let customers decide what insights to gain from the data? Or could there be a path where eventually it lets users take specific actions based on the data?
评论 #15024802 未加载
seanwilson将近 8 年前
How do you go about evaluating the accuracy of the themes and action items? Do you create a test set with obvious themes and actions and check the results for example?
评论 #15021144 未加载
forgotmysn将近 8 年前
would you say that your solution provides a sentiment analysis, similar to Quid, or do you focus on action items and things that product managers can actually address?
评论 #15020891 未加载
AznHisoka将近 8 年前
I saw there were samples but is this similar to how BloomBerry comes up with &quot;topics&quot; for popular questions for a keyword? They use some sort of NLP extraction of noun&#x2F;verb phrases.<p>Example: Most popular topics&#x2F;themes related to Vodafone: <a href="https:&#x2F;&#x2F;app.bloomberry.com&#x2F;questions;q=vodafone" rel="nofollow">https:&#x2F;&#x2F;app.bloomberry.com&#x2F;questions;q=vodafone</a>
评论 #15024786 未加载
pj_mukh将近 8 年前
This is super cool, I also appreciate the demo&#x27;s you have on your website (airlines, MBA schools etc.). Makes the end result super clear.<p>I don&#x27;t know much about NLP but are you <i>only</i> using unsupervised learning on the raw data? I would think you would need an NLP layer as well that sorts out basic synonymical issues, phrasing differences etc.?
评论 #15021080 未加载
bberenberg将近 8 年前
Are you planning to provide your service as an API to other companies that want to wrap a product around your work?
评论 #15021712 未加载
评论 #15021730 未加载
bitL将近 8 年前
Congrats and good luck!<p>I work on the same, just for my own company to automate customer interaction (well, at least 99% of it).
评论 #15022763 未加载
hobolord将近 8 年前
Congrats on the launch! I think I saw you talk recently in NZ, sounds like you have an exciting path forward
评论 #15025211 未加载
0xbb将近 8 年前
You guys hiring? I&#x27;m not a PhD or anything, just an undergrad with an interest in NLP.