The Modality of Search (Take 2)

After presenting at conferences in the US and Europe, I have made some minor modifications to the ‘Modality of Search’ model I posted a few months ago. Version 2 below. This proposes a new way in which to view Enterprise Search and Discovery Capability.

Link to PowerPoint and Explanation in SlideShare Click Here

It is early days, but there is some evidence the model and narrative is capable of changing the mind-sets of senior executives, leading to a different strategy and investment approach being taken towards ‘search’ within the organization.

modality-of-search-model-v2

GeoScienceWorld

gsw-photo

Delighted to be appointed to the Board of Directors of GeoScienceWorld (GSW) in the capacity of researcher-at-large last month. GeoScienceWorld is a non-profit collaborative for research and communications in the earth sciences.

GeoScienceWorld was founded by the American Association of Petroleum Geologists • American Geosciences Institute • Geological Society of America • Geological Society of London • Mineralogical Society of America • Society for Sedimentary Geology • Society of Exploration Geophysicists. More here: http://geoscienceworld.org

 

Teaching machines about a subject like oil and gas

Many organizations are sitting on a wealth of unstructured text. There are many OpenSource and free tools than can help build large scale associative networks in either unsupervised or semi-supervised ways.

With exponentially increasing volumes of information, much information is being ranked or suggested by popularity. That may effectively ‘censor’ some information through its obscurity. With an increasing need/intent for search engines to ‘show me something I don’t already know’ there appears a need to revisit ‘relevance’ algorithms. What is most popular, is not necessarily what is most interesting.

Search engines may be increasingly the way in which ‘we come to know’. If a corpus is the starting point, allowing the user to explore associative networks in various ways (not just by popularity), as a series of click-able facets, may mitigate the issues presented with a classic search box, where a searcher may be hampered to find out what they don’t know by their own existing knowledge of keywords. In other words, the agency of the searcher using traditional search engines may limit their ability to discover something they have no advance knowledge of. Exploiting associative networks may be a useful way of discovering new knowledge.

More here at LinkedIn: https://www.linkedin.com/pulse/teaching-machines-subject-domain-paul-cleverley?published=u

Slides and references: http://www.slideshare.net/phcleverley/teaching-machines-about-a-subject-domain

 

Modality of search

As part of my PhD research I have been exploring search technology, search driven applications and the modality of use cases. The model below is a suggested continuum of use cases.

Search Modality

The model above encapsulates ‘classic search’ in the bottom left hand corner, providing lists of results (web pages, documents) to meet an existing need. Precision (accuracy) dominates. Internet search like Google and library search technologies would fit here. Such information needs may include ‘I need to find the Group Investment Proposal for Project Orange’, ‘I need to find the company Video Tube site’. Above it in the top left hand corner, we move from these containers of information (web pages, documents) to entities, concepts and associations, providing simple factual ‘rich’ answers to questions. These may include answers to questions such as ‘What is the Capital of Australia’, ‘What is the current exchange rate between the dollar and sterling’, ‘Where is Aberystwyth?’. In these two scenarios, search is often perceived as a time saver (although there may be another way to find that information), facts are facts, independent of the individual performing the search, there is a perceived ‘right answer’.

In the bottom right hand corner the focus is on personalization of some form (to individual, transaction or task). There is not necessarily a ‘right answer’, it is subjective, what one person may find useful and interesting, another may not. Pertinence and popularity, rather than accuracy dominates. Knowledge is constructed in the mind of the searcher, a new need may be stimulated by the search technology. Task based portals and social networks using usage analytics driving activity feeds are encapsulated in this area. In this way you may find out about an upcoming conference in your discipline that you were not aware of, because the blog notification of one of your colleagues has been pushed to you via your activity feed.

Above this, in the top right hand corner the focus is on concepts, entities and associations but with more sophisticated knowledge engineering and statistical techniques adding context. These techniques can enable ‘search’ to suggest and recommend, to perform some form of analogical reasoning. Content analytics, although used throughout the model, is probably most important in this sector. What is unusual as an association, may be as valuable (if not more so) than what is most popular. For example, you may be interested to see geological formations anywhere in the world where an igneous intrusion sill has changes the properties of a limestone oil reservoir. A search based application could return these ranked by ‘most similar’ using the textual co-occurrence patterns around geological formation names.

This right hand side of the model supports creativity and learning, rather than just time saving. The bimodal nature of search.

Information Architecture (IA) and Information Management practices underpin this modality, without quality in these areas, any resulting search outcome is likely to be sub-optimal. This technological and architectural framework is enabled through a socio-organizational ‘soup’ of sub-cultures and competence. The role of information literacy and sensemaking of staff, may be just as crucial as the technology when assessing enterprise search and discovery capability.