Re: [xmca] Psyche Mining - Cross Culture Decision Making Activities

From: Naeem Hashmi <nhashmi who-is-at>
Date: Tue Jun 26 2007 - 15:46:27 PDT


Thanks for the feedback. I see great need for such basic research. Today, Internet based advertisement applications use embedded intelligence (derived through basic data mining models) through use of Cognitive patterns. I had discussions with leading Internet Ad companies on design of such solution... Due to NDAs I can't disclose how they do it. But the way business is evolving in the future - distributed across the globe through [web]services - will use very different application architectures than what we use today. Its all about use of integrating knowledge back in the business system to make intelligent decisions to improve profitability.

CRM (customer relations management) tools today classify certain calls/complaints through voice pattern analysis and content mining. Then they use the derived knowledge to improve 'future' customer support/responses...and increase revenues. These are a very simple and real practices today. Most algorithms used today are designed to mine 'english' content even if source is in different language... and here one 'losses lot, especially the emotions, in the translation'. Moreover these mining tasks are 'word frequencies driven without much context of when the dialogue was captured (business process stream). As we move toward global (culturally mixed) collaborative business, the need for cultured-centered decision making process will be extremely important.

Last year, during one of my workshops on data mining, I used US department of Highway Accident database for analysis. This database had structured content (car model, driver, age, location, deaths, etc..) and textual description. As part of analysis, you use clustering techniques to understand how an accident was described (and state of mind) and then you bounce discovered clusters against structured information to identify root causes of accidents accurately. Most applications today deal with historical data, no geo-global context and when you add geo dimension, one must consider the cultural-psyche as well -- but all to be done almost in real time. Homeland-Security and DOD folks are doing some research on Gesture mining (today, used for soldiers to expose them with Arabic gestures) but they are very limited in scope (in lab) but I believe such research will end-up is business domain at some time.

Yes. I agree, this is such a complex proposition and the blanket terms need a lot more detail explanation which I am planning to include in my next book 'analytics design strategies.' However, the intent here is to take culture-induced-cognitive science and blend it with the art of 'application design' for future business applications. I always have taken a very complex ideas and brought them in the real world in the applications domains... I am new to this group and eager to learn.. but in reality I am an Experimental Nuclear Physicist, Radiological Health Physicists and Environmental Scientist with 8 years in academia (including Dartmouth) and 20 years in Technology Development (DEC).

How real this concept is? I say very real in next 6-10 years. Baby solutions (as discussed above) are here today. I advise technology providers (SAP, and many more) on their product visions and architecture. SAP is world largest software company. I was one of the architect to help SAP design their Business Intelligence (BI) an CRM platform. The BI is most important component of overall SAP's future applications. So I see a huge opportunity of 'Psyche-mining in the years to come. But success depends on basic research first. This is what the purpose of Center of Knowledge Engineering is all about and I look forward to learning from 'Cross Culture Decision Making Activities" group.


  ----- Original Message -----
  From: Mike Cole
  To: Naeem Hashmi ; eXtended Mind, Culture, Activity
  Sent: Tuesday, June 26, 2007 4:49 PM
  Subject: Re: [xmca] Psyche Mining - Cross Culture Decision Making Activities

  Interesting entry into XMCA, Naeem.
  I am reasonably acquainted with both Friedman's writing and the research on cognitive styles to which
  you refer. While I find both areas interesting and challenging, I do not think either can be understood
  in the more or less blanket terms that you use. And I am virtually certain that there is no clear connection
  between the basic research on West-vs-the-rest cognitive styles from quesionaires and experimental
  tasks to business applications of the kind you are concerned with.

  Do you know of any successful such applications?

  mike cole

  On 6/26/07, Naeem Hashmi <> wrote:
    I come from business–technology research community end, engaged in developing new technologies to address global business-communication challenges. The following note introduces an interesting challenge for researchers today.

    As world is getting flatter and flatter, how well we understand communication, collaboration and decision making mechanism, almost in real time, will determine the success of the future business. This means understanding eastern cultures (collective intelligence – social, decision making processes - emotional intelligence, gestures etc.) and with direct interactions with his/her western counterpart at an individual/group level. This requires teachers to be first 'globalized' so they can bring young generation accordingly. (Perhaps many readers of this forum may have read Tom Friedman's' book, "The World Is Flat." Tom's book is an interesting reading but for those who have not, here is Toms' talk at MIT that you will find interesting.)

    However, business cannot wait for the future flattened-generation in this geo-political world; we need technologies today to facilitate this globalized-business. Last year, I launched a research program (Psyche Mining) at the Center of Knowledge Engineering at National University of Emerging Sciences and Technologies in Pakistan ( to develop new algorithm to solve global business communication challenges across the globe in real-time (distributed autonomous agent technologies). Main research is how to capsulate intra-cultural behaviors, especially eastern vs. western, in context of business decision making processes. I have few graduate students working on new algorithms.

    Here is how I described a simple scenario for a cover story that I authored for the Enterprise Magazine (June 1, 2004).

    "Today, when customers call to address problems or follow up on unresolved problems, they usually end up interacting with voice-response prompting systems, which put them through sequences of prompts, and eventually to customer service representatives. By the time customers reach live representatives, they're already frustrated. Further delays and unsatisfactory answers stoke agitation, eroding customer confidence and possibly causing the company to lose business. Is it possible to turn such a situation around?

    Let's fast forward a few years. In a future version of this scenario, before the customer gets upset, embedded mobile intelligent agents pick up the conversation pattern and voice tone change. The system proactively addresses the rising anger by playing an appropriate subliminal message that calms both the caller and the customer rep before it gets too late. This "intelligence" is built right in the "communication" layer, where an intelligent agent performs voice mining on the fly to understand not only the language, voice envelope, and culture involved, but also the psyche of the caller. The system understands the customer's behavior with far more sensitivity than what's possible with today's customer profiling techniques."

    Full story is available at

    The Psyche Mining research project includes the following key elements in designing new algorithms: Speech Mining; Language development; Content Mining; Gesture Mining; Culture-Mining; Decision Mining, all in real time. The proposed distributed agents spread across the communication threads (at the participant's nodes) just like virus that has built-in intelligence to collect 'ambient intelligence' and when combined with past 'collective intelligence' understand the direction of the discussion and act accordingly. These agents collaborate with other agents associated with participants engaged in real-time communication (collaboration). One can identify locale of a percipient relatively easily through IP address schemes that can be then turned into 'geo' dimension in turn identify unique cultural characteristics associated with individual participants and much more.

    We had some success in developing algorithms in emotion extractions through content mining, but a lot more needs to be. Project is just in its early stages

    Here are few questions for this group.

    Are other universities engaged in similar research? If so, what has been learned?

    Any references to research on how different cultures make decisions and why? For example decision making process, from childhood, in eastern cultures is 'community' based (team efforts, concession driven) while in the western cultures, decision making based on 'individuals' opinion (me, my, I). How both decision making styles work in a global business decision making? What are the key culture (social) qualifiers responsible for decision making activities?

    Internet Advertisement companies do exploit brain-wave response model (say P300) to pop specific ads based on decision cycle based on product price. Say for car, the decision process is different than when buying a bicycle and how far-apart you need to project an ad to catch your attention is executed based on how P300 brain-wave triggers emotions. This is achieved through mining past visits history and much more…but not very robust and very incomplete process due to mobile nature of the end users. The Psyche Mining project will also help in such real-business scenarios at a global scale.

    Do you have research data on how 'collective-intelligence' influences 'social-intelligence' and how they are both related to 'Emotional Intelligence' specifically decision-making actions (possibly for cross-culture domain)?

    Any feedback is welcomed.

    Naeem Hashmi
    Chief Research Officer
    Information Frameworks
    T: 603-552-5171 M: 603-661-6820
    xmca mailing list

xmca mailing list
Received on Tue Jun 26 15:49 PDT 2007

This archive was generated by hypermail 2.1.8 : Sun Jul 01 2007 - 00:30:04 PDT