I’ve been told for the past year not to use the “I” word, “intelligence”. Oh f’gods sake. IMHO NGOs haven’t, are not, and are certainly not intending to, collect any form of intelligence about people, nations etc. But they are starting to build assisted intelligence systems, as in computer systems that help human beings make decisions by improving their access to information.
And some of the techniques used in intelligence systems also turn out to be very useful for working out what’s happening in a crisis, i.e. who needs help where and when.
So let’s put on the big-girl pants and look at what these are, and how they might be used to help people in crises (as opposed to, say, make them nervous enough to stick tinfoil to their ceilings).
I noticed the term “development intelligence” being used more often this year (and no, not by us). Mostly, it seem to cover information about NGOs (also here) rather than information about the people they’re trying to help. It’s also a term used about software development intelligence but that’s not really related.
But people are starting to use it for the process of gathering and processing information to help people in crisis, and if this term sticks we need to think about what it is, and how it differs in spirit from the military intelligence that we’re terrified of being confused with. A few suggestions about this are:
- First, there is no enemy. Military intelligence presupposes an enemy: NGOs are not fighting someone, and are not taking sides in a conflict. The only opposing forces at work against them are usually mother nature (cyclones, floods, droughts etc) and economics (economic depression, unemployment, economic migration to marginal land etc).
- Deception happens, but is rare. Yes, fraud happens and mistake happen but there isn’t the all-out watchfulness for counterintelligence and massively false information that military intelligence always has to be aware of.
- Threats happen, but aren’t usually propellent-based: disease, further natural disasters (e.g. mudslides) and secondary effects (e.g. nuclear reactors breaking) are much more likely events and aren’t likely to be ameliorated by keeping the other guy out of your area.
- The end goal is not for one side to ‘win’ whilst someone else ‘loses’ (my apologies to those military people who are simply trying to understand what is going on in their worlds). The end goal is to avoid crises, or if that can’t be done, to mitigate their effects. Nobody ‘wins’: we’re trying to help people not lose as much as they might have done.
Intelligence analysts are experts at turning raw data into actionable knowledge, i.e. information that people can use to help them make decisions. In our case, those decisions are things like “where do we put the food supplies” and “which hospitals do we send our earthquake casualties to”.
To make these types of decision, you need to know what’s happening, where and to whom. Things like where the hungry people are, which hospitals are still operational (and where all the field hospitals with equipment x are). The NGO community has made a start on this with its 3W (who, what, where) methods – basically listing which NGO agencies have placed which resources where on a map – but this is a very early form of something that intelligence analysts know as situation awareness (or sometimes situational awareness – the difference between them is so fine that the terms are often confused). There’s a lot of good literature on situation awareness (and quite a few systems too), and it’s time we started reading some of it.
Intelligence analysts know a lot about data too: where to look for it, how to get more, how to talk about how true they believe data and the sources that produced it are, how to make sure those beliefs are preserved so we don’t get statements like “Iraq can attack us in 45 minutes” getting through without checking (ah whoops).
And one of things they’ve done is classify the types of data that are available. I’m not advocating that NGOs start using terms like HUMINT and SIGINT, but it won’t hurt for us to think hard about the types of data source that we have available to us, the types of data that we can legitimately be interested in (and conversely which sources and types of data we should avoid using) and the issues that are important to each of them. Some of this has already happened in journalism, where ideas like stringers (trusted sources who don’t work for a specific new organization) and careful data provenance recording already have a long history.
Analysts also know a lot about the process of collecting data. Many people are now aware of Boyd’s OODA loop (observe-orient-decide-act), originally used to describe the cycle of thought that pilots went through in a dogfight. Fewer people are aware of and use the Intelligence Cycle and its variants. This is a great shame, since it describes the steps that analysts take to create actionable data (note that it doesn’t include action – there are separate models for that). Again, there is a lot of literature on this, and again these would be useful things for people dealing with crisis-related data to read.
Sometimes data is just data: it won’t magically tell you that something is wrong, or that there’s something you need to be aware of, no matter how much you collect and however many processes you apply.
But you can start asking questions with data, and one of the most common ones is “what if”. An analyst faced with a situation will often start forming hypotheses about what might be happening in the world, about why a situation has developed in a certain way etc. This hypothesis formation is part of what we’ve formed Hunchworks from. And when there are more than one hypothesis about an event or situation, there’s an argument. Analysts have created a tool to decide between them called Analysis of Competing Hypotheses. There are also other forms of assisted (and augmented) argument system being used by intelligence analysts, but ACH is one of the most common ones. And also worth a look for analyzing some of the “what ifs” being faced daily by NGOs.
And last, systems. This is not a definitive list of systems that we can learn from (my memory is still suffering from Christmas), but I will add to it as I remember places, companies and people who can help.
• IBM Big Sheets, which is part of Big Insights
• Xerox Parc’s ACH (open source)
• IBM Watson
There are also discussions to be had about other techniques like imagery analysis, uncertainty handling, cognitive and cultural bias, but many of these areas are already covered by emerging (and existing) work on crisis data handling.