Hey wiki comics is advertising some pharmacy links you can find below. Sorry for any inconvenience. Hope you can understand... Links are below: Tadalafil Citrate | generic cialis 10 mg | tadalafil citrate 10mg | tadalafil citrate 5mg | generic cialis 40 mg |

Society - Written by on Tuesday, September 22, 2009 8:48 - 10 Comments

Naumi Haque
Charting emotions

One of the emerging themes from our research is the notion of the “highly-instrumented” enterprise environment. Data is everywhere – new types of data that we didn’t previously have access to. You can think of this as a virtual layer of information that adds a new level of understanding (and complexity) to the physical world. Of particular interest to me is the notion of sentiment analysis, where companies can use tools from vendors like Attensity, Scout Labs, Radian6, and a variety of others to listen in on customer conversations and measure sentiment towards products, services, brands, and specific experiences. Companies can now analyze every tweet, blog post, and comment to know what customers are feeling. This is definitely cool technology.

What’s equally impressive is some of the display technology being developed to display this type of data. All vendors have some form of executive dashboard, but these are highly utilitarian. From what I have seen, the bar for sentiment visualization is being set by other innovative thinkers. For example, ongoing projects like We Feel Fine from Jonathan Harris and Sep Kamvar as well as Bio Mapping from Christian Nold aim to visualize emotional data in new, interesting, and useful ways. We Feel Fine is more of an art project than a rigorous sentiment analysis tool, but it provides a useful example for how we might organize, display, and search for comments. Users on We Feel Fine can search by emotion (key word only), gender, age, location, weather, and date. It also connects emotions to associated images that are found within the document.

Bio Mapping (shown below) uses a lie detector connected to a GPS unit to measure location and physiological arousal at the same time. This is then plotted using Google Maps and other visualization software. Note, in this case the sentiment metric is intensity of emotion, not the specific emotion itself. The spikes shown on the map are locations of interest, but that is all we can determine from the data.

Although most of the complex visualization technology is still nascent you can imagine where this is type of analysis is going. Companies could segment customers based on emotional response, plot the spread of viral buzz, identify ideal test markets, and optimize local campaigns based on near-time feedback loops. Employees could gain access to a new lens on customer activity, behaviour, and satisfaction in a user-friendly display that makes analytics fun. Large retailers could use similar mapping technology powered by emotion data to optimize store layout and measure display/product appeal. The biggest challenge to wide adoption of these types of tools is the lack of valid emotional data in significant volumes. Currently, mining user comments online is the best available data source, but some early research suggests promising breakthroughs in the area of voice analysis and facial recognition as well – stay tuned.


You can follow any responses to this entry through the RSS 2.0 feed. Responses are currently closed, but you can trackback from your own site.

Sep 22, 2009 9:54

Naumi – I’ve always been a big fan of connecting visualizations for data. In fact, I’d like to see more device-delivered examples. Everything from that mood globe that one could set on their desk indicating the sentiment of traffic related to alerts/posts on their keywords. All the way to visualizations of movie review sentiments, that would tell you at quick glance more than thumbs up/down, but provide a sense about if it will more likely fit one’s tastes (quirky, dark, cynical, feel-good, etc.)…delivered via an iPhone (or smartphone)display, of course.

Cognitive Design » Blog Archive » Harvesting Human Feelings
Sep 23, 2009 19:27

[...] [...]

Oct 10, 2009 17:14

Interesting post! We’ve just launched our sentiment analysis tool that captures facial emotion for market research and mood tracking. We plan for a geographic mapping of status in real time, a kind of distributed mood ring. To your list of enterprise applications, we’d add health tracking and early predictors of market shift.

Wikinomics – A future vision of CRM
Oct 16, 2009 9:35

[...] Listening platforms and sentiment analysis tools allow companies to capture customer preferences, complaints, feedback, and queries expressed [...]

Erik Van den broecke
Oct 27, 2009 3:44

Very revealing article! I totally agree that we will be “blessed” or “confronted” with a new virtual layer of information, and people indeed can transform this new information in many new insights, creating a new level of understanding.

Somewhat further in your article, you mention , between brackets, : (and complexity). And this complexity is what is interesting me:

Would it be possible to exchange ideas on this ? I would like to understand what you mean by “complexity” in this context. I would say that it adds to the number of “non-random” relationships that can occur between people using this new layer of information. So the level of “organized” complexity increases. And if the theory is correct, we should then witness an increase of emergent phenomena. The only thing is that I have not yet come across examples of this new ”feeling information based” emergent phenomena. Perhaps you have already spot some examples.

The reason for my interest comes from a conference “Complexity: Friend or Foe”,that I am organizing December 16th in Brussels, Europe. The seminar will focus on two topics : “complexity and mechatronics” and “complexity and wikinomics”. We (the Flemish Society of Engineers, http://www.kviv.be/unidentified/over/kvivinenglish.aspx) have been able to attrack a big name as key note speaker : Geoff West, chairman of the Santa Fé institute for complexity research.

Perhaps there could be an opportunity to involve your “charting emotions” case in the conference. Since we have to freeze the conference set-up soon, it would be nice if you could contact me quickly. You can reach me by mail or skype (erik.van.den.broecke)


Naumi Haque
Oct 27, 2009 11:43

Hi Erik,

Thanks for the interest in the research. In this instance I was thinking of complexity in relation to the amount of data and the fact that the vast majority of new data sources produce unstructured data – comments, video, voice, images, etc. So, as I mention in the post, we are privy to new levels of understanding, but in order to get this understanding we have to distill it from a many different types of raw data.

The other part of complexity is that the unit of analysis has grown considerably. When everything was local, we only cared about data from small groups, local geographies, target customers, and specific competitors. Now, the unit of analysis is the world. Everything is connected and so conducting trend analysis and identifying causality is extremely difficult.

The last thing I would say about complexity is that because the data being generated is unstructured and not tied to a predefined taxonomy, what you find is new information about virtually anything and everything imaginable. I read an article from some scientists at Google recently called “The Unreasonable Effectiveness of Data.” While much of it was over my head, what I did gather was that the requirement to seek out specific data is reduced because the corpus of existing digital data is so huge (the example in the paper was of text analytics), that we can find patterns related to whatever topic we might be interested in. This is tied to your notion of emergent phenomena. I think you’re definitely right about seeing more of this. As an example, sentiment analysis tools for customer analysis have a far greater scope than market research. In traditional market research, you have to identify the trend you are looking for, then design a question set, and finally find subjects to query. With sentiment analysis, you are mining the existing conversations of customers and prospects and using this large pool of data to identify trends (assuming your company is big enough and you have a large enough pool of customers). In this case, questions you never thought of asking will be answered and topics you never imagined will emerge.

Of course, as you noted, there are probably many more layers of complexity at play here. I think we’re just starting to scratch the surface : )

Wikinomics» Blog Archive » Color coding the Internet
Nov 3, 2009 13:08

[...] would be like emotion mining – in real time, upfront and [...]

Wikinomics – With So Much Data, Why is Work Getting Harder?
Mar 23, 2010 10:22

[...] continue to study how organizations can flourish in this new world of unbounded data. Specifically, Naumi Haque has spent the last year studying sentiment analysis including the tools and processes that best [...]

Jonas Lind
Sep 13, 2010 9:49

This might also be relevant. There is a research program in Stockholm Sweden called Mobile Life, where some of the projects are related to working with emotions.

I wrote a blog post last year about it:


Sep 14, 2010 9:41

Thanks for the link Jonas – lots of interesting projects to dig into! I like the Affective Health idea and it looks like they have some good videos on their blog as well.

Now available in paperback!
Don Tapscott and Anthony D. William's latest collaboration, Macrowikinomics: New Solutions for a Connected Planet. Learn more.

Business - Oct 5, 2010 12:00 - 0 Comments

DRM and us

More In Business

Entertainment - Aug 3, 2010 13:14 - 2 Comments

Want to see the future? Look to the games

More In Entertainment

Society - Aug 6, 2010 8:19 - 4 Comments

The Empire strikes a light

More In Society