Does sentiment analysis tell us whether Chromebooks are a good idea?

Does sentiment analysis tell us whether Chromebooks are a good idea?

Summary: The debate surrounding Chromebooks rumbles on. Can we use machine learning to tell us once and for all whether to get on-board with the idea?

TOPICS: Laptops
Chromebook - Positive or Negative
Chromebooks. Are they a good thing, or a bad thing?

In our industry, we're all pretty opinionated.

This is a good thing in that it creates debate, but not such a good thing when it comes to actually deciding things. It would be good is we had some definitive way of knowing that iOS was better than Android, or that this year will be the "year of Linux on the desktop", and so on.

On these very pages over the past week or so my ZDNet colleagues have been debating whether the Chromebook is a good idea or not.

And it's not just on these pages -- in peer publications around the web the Chromebook debate is raging. Plus, it's all kicking off on Twitter.

The question is -- can we apply some science to understanding whether the Chromebook is a good idea.


In theory, we can use something called "sentiment analysis" to look at text and understand whether an article generally positive, generally neutral, or generally negative. Is we look at all the articles on a topic, we can say whether the corpus in its entirety is generally positive, generally neutral, or generally negative.

You can also do the same thing with social networking artifacts, such as tweets. In theory, if we had a sentiment analysis engine we can feed all this content in and come up with a definitive "Yes, Chromebooks are the awesomest!" or "No, Chromebooks are epic fail!" 

Does it work? Having done it, I'm not sure. Let's go through things together and have a look...


Back when we all used to argue about whether Windows 8 was a good idea or not, I wanted to use sentiment analysis to get a "definitive" answer. At the time, I decided this was way too difficult to bother with.

What I'd forgotten was that we software developers can now get away with being incredibly lazy, and avoid having to understand how anything works by simply wiring together web services.

I found a sentiment analysis service from Datumbox that looked like it would do what I needed. They offer a number of APIs, and they have two for sentiment analysis -- one for long-form content, and one specifically for tweets. (Tweets are short, and hence sentiment analysis needs to be differently tuned.) All I had to do was get the content and throw it at the service for analysis.

I firstly wrote an engine that would go out to Google News and find articles on Chromebooks from ZDNet and a number of peer publications. 

I then wrote another engine that would go out and get tweets that mentioned "Chromebook". This ended up being pretty interesting. For one thing, I got a lot of non-English tweets that would throw off the sentiment analysis, and hence used a language service called Detect Language that I would use to chuck away any non-Englsh language tweets. Also, loads of the tweets ended up linking to articles rather than being straightforwardly opinionated comment from the masses. Most of these articles tended to be spam (giveaways. etc). Thus I also chucked away any tweets that contained links.

Taking a relatively small sample of 101 tweets that were just English language comments without links, we get examples like this:

Flagged as positive:

  • "Yes I got my Chromebook!"
  • "Got a #chromebook 11 for my birthday - best present ever."
  • "You guys, the Chromebook is everything."

Flagged as negative:

  • "Anyone got a #chromebook HP 14 'Haswell'? I want one #technology #google #laptop"
  • "my chromebook is always dying or dead "
  • "Successfully running ubuntu on my chromebook after weeks of command-lining the thing phew #Geek"

Flagged as neutral:

  • "Tweetin from my Chromebook."
  • "Anyone own a Chromebook?"
  • "Anyone have opinions on iPad vs Chromebook for portable #writing? Any writers use either? #nanowrimo"

Does that work? I'm not sure -- the above is just to give a flavour, but even having spent hours looking at the sample set manually, I can't necessarily make sense of the data. It probably doesn't do much worse than I would do if I was manually sorting them. Anyway, of the 101 sample tweets, this is what I got:

Sentiment Analysis - Twitter
Sentiment analysis of tweets related to Chromebooks.

This suggests that half the people out there talking on Twitter about Chromebooks aren't that enamoured. But I'll come back to that.


If we look at the ZDNet content and run a sentiment analysis on that we get some interesting results.

It sort of works.

James Kendrick recently wrote "Chromebooks: Sometimes less is more". I wrote "The Chromebook -- it's like an iPad, but with a keyboard" a while back, and Steven J. Vaughan-Nichols wrote "Low-end laptops:The rise of the Chromebook". These were all correctly flagged as positive.

Ed Bott's article "Latest IDC figures show Chromebooks continue to struggle" was correctly flagged as negative.

David Gewirtz's article "The Chromebook, Windows RT, and the Officebook that might have been" was flagged as negative, although it say it should have been neutral.

An oddity was that David's "Why there are at least two great reasons to buy a Chromebook" was negative (when it's positive), and Larry Seltzer's "Why there's no good reason to buy a Chromebook" was flagged as positive (when it's negative).

Taken together, we get this:

Sentiment Analysis - ZDNet
Sentiment analysis of ZDNet's Chromebook coverage.

So at ZDNet, we seem to be generally more positive about Chromebooks.

What about if we expand that out to look at our peers? We get this:

Sentiment Analysis - ZDNet and Peers
Sentiment analysis of Chromebook coverage from ZDNet together with its peers.

Much more positive. But this point though it's worth pointing out that most of our peers' content on Chromebooks are reviews of actual devices. ZDNet's coverage has tended to be more analytical of the whole Chromebook proposition. Chromebooks tend to review well because they are cheap and good at what they do.


The question is, have we learnt anything here, either about sentiment analysis or about Chromebooks?

Sentiment analysis is very interesting when we look at customer support over social media, and also big data. It helps to be able to zero in on set of people within a wide audience who are either flag bearers for your brand, or who are struggling.

What it gives you though is very fluffy, especially if you're the sort of software engineer like I am that likes very black and white results. It seems to get things mostly right.

And to the question, can we use sentiment analysis to tell us whether Chromebooks are a good idea or not?

In the rarified position of writing about technology, it appears that we bloggers and writers are more positive about Chromebooks than actual users because we're either a) thinking about them from our specialist perspective, or b) we're reviewing them.

But, with the context that I have from having fiddled with the tweets for hours getting the engine to work properly, most of those people tweeting tended to be students who have been given them to work on. So I, with a more intimate knowledge of the working set, have a better idea as to what the data means.

I'm not sure I'm any clearer as to whether Chromebooks are a good idea or not having done this. How about you?

What do you think? Post a comment, or talk to me on Twitter: @mbrit.

Topic: Laptops

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • Chrome Books. I still don't get it....

    Chrome Books are over 90% reliant on the internet to be a productive option. That is not the fault of the product but of the Chrome OS which I consider to be a glorified Web Browser. Fine if you have access to broadband internet but a pretty useless if you do not.
    My personal choice would always be a MacBook. A non-Retina MacBook Pro. is the ideal choice for the heavy user being resilient to knocks and robust while being a highly productive machine.
    • define

    • Retina MacBook

      Why dis the retina MBP?
      • Probably because of the additional power ...

        ... requirements for supporting the higher resolution screen.
        M Wagner
  • Readers of tech magazines don't like change

    Technology journalists and reviewers like Chromebooks and overwhelmingly give the Chromebook a positive report.

    Readers of technology publications tend not to like change (such as those commenting below). They have often used a particular computer platform all their working life, and have invested a lot of time in a legacy platform.

    That's why so many readers and commenters deny that the Post-PC era is upon us (even when it is obvious). That's why a lot of readers / commenters vehemently support legacy PC platforms, and are afraid of new things like the Chromebook.

    The Chromebook represents the 'thin client' that Sun Microsystems predicted in the 1990s would take over. The only surprise is that the Chromebook didn't appear earlier.
    • Sun Thin Client

      It's been a long time since I've used a Sun thin client (1994ish) but when I did, it was more like a Windows Citrix/Terminal Server thin client. The Chromebook is a browser-based mobile application platform. A mobile application such as those in the iTunes or Google Play store are significantly different than a Sun thin client. In fact I'd argue that we'd be closer to Sun's vision than we are now because Apple created sort of a Renaissance in terms of creating apps that must be installed and have local function without a connection vs. those accessed through a browser or thin-client computing endpoint. Although all are heavily dependent on back end services, Citrix/RDP/X-Windows don't work at all without a connection but HTML5-based browser apps and the Chromebook have some function without a connection.
      • "have some function without a connection"

        That's the problem "...some..."
    • Work….

      Do you actually work on a computer? There are bare bones work environments where a "thin client" may do the job. But many people need more robust tools, for which a computer - and not a tablet, by the way - is essential. The simple fact is that, despite all the "post PC" hoopla, there is room in the marketplace, and in the workplace, for more than one platform and device. In other words, in the real world, Chromebooks, iPads, laptop computers and desktop computers can, and do, coexist, if not always harmoniously, as least functionally. It's not an either/or proposition, despite what some tech journalists would have us believe. Either/or makes a good headline or book title - it's great link bate, but it says more about the author - or editor - than it does about the place most of us live in day to day.

      Is the Chromebook a good idea? Clearly for some people it is. For others its just not adequate. Hence the author's cloudy conclusions.
    • Tech writers have vested interests.

      Tech writers have vested interests either in particular technologies that they are tasked with writing about, or by virtue of industry affiliations that they are tied into. That is why they don't like change. It is probably better to monitor customer sentiment to determine whether something is good or not.

      An example of this is Windows phone which a lot of tech writers wrote very positively about. Customer sentiment on the other hand gave it a big thumbs down, and it bombed in the market.
    • Thin clients

      we use mainly thin clients here - connected to Windows Terminal Server or Linux servers. Some users have notebooks because they travel or need to provide support from home.

      The Chromebooks, with an RDP service, could replace the thin clients, but wouldn't bring any advantage - going from a 24" screen to a 13" screen is a backward step for non-mobile users, as is the cramped keyboard and touchpad. For the mobile workers, it doesn't bring any advantage -they have a notebook, because they need local access to the applications they use, when they aren't attached to the corporate network.

      In native Chromebook mode the most the users could do is check their email, everything else requires Linux or Windows applications.

      Moving to a ChromeOS based device means re-writing a lot of the infrastructure that is currently in place. This is where ChromeOS either makes sense or it doesn't. If you already have a majority of your LOB using a web front end or in a cloud solution, then it makes sense.

      If you are still running most of your systems through local applications, then it is a huge investment that the minimal price difference per device won't make economical.
  • Does sentiment analysis tell us whether sentiment analysis is a good idea?

    Just curious... ;)
    • :)

      good one.
  • I think Sentient Analysis is a better choice

    I feel ambivalent about sentiment analysis.

    I feel Chromebook is too limited but has a chance of success anyway which is sentiment about the community health of sentient beings whose future is a version of The Matrix.
    • No more limited than Android was in the beginning.

      Think of a Chromebook as a tablet with a keyboard/touchpad.
      M Wagner
      • And without the apps...

        ZDNet keep saying that Windows RT and WP8 will not succeed, because they don't have the apps that iOS and Android have.

        Yet ChromeOS should be a success, because it is like Windows, but without the apps? How does that work?
  • Who determined the labeling criteria?

    Flagged as negative:

    "Anyone got a #chromebook HP 14 'Haswell'? I want one #technology #google #laptop"

    What?? I don't get why this is flagged as a negative comment for the Chromebook.

    Nor this:

    "Successfully running ubuntu on my chromebook after weeks of command-lining the thing phew #Geek"

    Lots of geeky Chromebook users like to install Linux distros on their device and switch back and forth between the OSes. I don't see how that is in any way a negative for Chromebooks that easily allows for that possibility.

    If you want to do a real sentiment analysis, you have to go no further than looking at the actual Amazon reviews and ratings for the devices. They are overwhelmingly positive. (Keep in mind dissatisfied customers are also more likely to write a review.) Your colleague, Ed Bott, just did a piece trying to spin Amazon ratings in a different direction but the fact remains that those that actually purchase and use Chromebooks are almost unanimously very happy customers.
    • The fist one...

      no idea.

      The second one is a fail for ChromeOS, because the user is "resorting" to running a second OS on the piece of kit.

      It might be a geeky achievement medal, but it is a black eye for Google.
  • Whatever happened to logic...

    …as a means of determining if something is good or not?
    P.S. Is there an Astroturfer filter on your sentiment analyzer?
  • will be buying a Chromebook

    I will be retiring next year and will be buying a Chromebook. I got a degree in Computer Science and started working with mini-computers, then Apple II, MS-DOS & PC-DOS. Since then I have been primarily a user working at a university library. But both IT people and users rely on me to "translate" between common description and tech-speak. I must say that most users are not concerned about hardware, software or OS as long as they can get their work done reasonably easily. We have some specialized Windows-based software. But most of the major software suppliers are putting their money in developing Web-based tools instead of client-based software. Also, more than 20% of schools are using Chromebooks. This means that in the very near future, we will be dealing with students (and some employees) who only know Chrome OS. How are we going to manage that transition if we don't at least get familiar with Chromebooks?
    • The three main reasons schools are using Chromebooks:

      1) They're cheap.
      2) They're cheap.
      3) They're cheap.