Detecting disruptive innovation in Idea Management Systems

Posted By on July 1, 2019

Lately we have had less updates to our Gi2MO software family and focused more on longer term research on Idea Management Systems. Today we are happy to share results of our latest experiments on idea organisation.

In the past, we presented several approaches for automatic selection of successful and/or interesting ideas (eg. via sentiment analysis or idea taxonomy). As the problem remains unsolved to a great extent, we still see this as valid direction for research. Yet, this time we would like to propose something quite different: search for disruptive innovations.

So what are disruptive ideas ? The term was coined by an American scholar Clayton Christensen and in nutshell pertains to innovations that redefine industries and shakeup the status quo of what was considered as successful up until then. Some examples presented by Christensen and others are: Netflix disrupting video rental market with online streaming; Apple iPhone disrupting the laptop industry as an internet access terminal; Wikipedia disrupting traditional encyclopedia market; Kodak falling victim to digital photography; or discounter marts such as WalMart disrupting department stores.

Looking at those prominent examples and the magnitude of their success, it seems like trying to find such ideas might be quite a good direction. So how to do that ? Christensen and other scholars exploring the topic, left us some hints by characterising and explaining how to identify disruptive innovation. Some notes we took and got inspired include:

  • disruptive innovations are not targeted at satisfying needs of well established customers in the industries they disrupt
  • disruptive innovations are very different from sustaining (incremental) innovation in well established companies which favour to retain their customer base
  • disruptors deliver innovations for overlooked market segments by market leaders

Taking note of those points, how can we contrast them with the motivations and content of companies that deploy Idea Management Systems? Aren’t those frequently established market players that not uncommonly would pretend to leader positions ? The same leaders that Christensen points as ones failing at disruption and falling victim to smaller companies ingenuity. Well, yes but turns out not always: examples of Apple and Amazon paint a different picture with those established enterprises portrayed as disruptors in new market segments relative to their core business.

Ok, so we are motivated and roughly know what to look for but given all that … how to actually make all this work in the technological reality of Idea Management Systems – how to find disruptive innovations in Idea Management submissions? After all, previous studies have shown the majority of Idea Management content is small incremental ideas that relate to satisfying needs to well attached customers. Wouldn’t it be hard to find disruptive innovations in all this mess, given they are such a minority and almost the exact opposite of what resides in IMS?

Well, our Gi2MO answer to disruptive innovation problem is Outlier Detection! In broad terms, it’s a technology that aids looking for anomalous data samples; researched since quite a long time with frequent applications in fraud detection, intrusion detection and hardware defects analysis. We see the capabilities of those algorithms to detect unique and rare data samples as an answer to finding interesting disruptive ideas that are nothing like the bulk of user submissions proposed in Idea Management Systems.

Connecting the theories of Christensen with the concept of outlier detection, we did a series of experiments, testing multiple algorithms and come up with some recommendations for most successful approaches and how to implement them in Idea Management Systems.

If you would like to know more we recently got a paper accepted for publication in a scientific journal called International Journal of Web Based Communities. The article describes all our experiments and results, under the title:

“In Search of Disruptive Ideas: Outlier Detection Techniques in Crowdsourcing Innovation Platforms” by A. Westerski and R. Kanagasabai. International Journal of Web Based Communities, 2019 Vol.15 No.4, pp.344 – 367

As soon as the full-text article is published by Inderscience and becomes available online in the next issue of the IJWBC journal, we will link the manuscript for download here.

Update: Article is now online available at Inderscience, optionally you can also get the pre-print version here.

New articles on Idea Management research from JSMO Journal

Posted By on March 16, 2015


For the past year, joined by a number of experts from Idea Management area, we collaborated with the Journal of Social Media for Organizations (JSMO) to bring an interesting package of articles that would report on the recent Idea Management research and interesting case studies of ongoing projects.

Today, as a result of this collaboration, we are happy to announce the release of a new Journal Special Issue entitled Large-Scale Ideation and Deliberation: Tools and Studies in Organizations.

In our vision, the effort to bring Idea Management into organisations is much more than just software. It entails setting up the proper processes, defining the open innovation methodologies and policies suitable for a given deployment, doing all the work to connect with the people who are going to provide the ideas; and many many more activities…

The four articles published as part of the journal explore those various aspects of Idea Management, yet are quite tightly linked to each other by driving inspiration from civic scenarios and case studies:

  • Five Design Principles for Crowdsourced Policymaking: Assessing the Case of Crowdsourced Off-Road Traffic Law in Finland by Tanja Aitamurto, Hélène Landemore
  • LiquidFeedback in Large-scale Civic Contexts: Framing Multiple Styles of Online Participation by Giulia Bertone, Fiorella De Cindio, Stefano Stortone
  • Understanding the Roles of Artifacts in Democratic Deliberation From the Citizens’ Initiative Review by Jess Kropczynski, Guoray Cai, John M. Carroll
  • A Roadmap for Open Innovation Systems by Mark Klein, Gregorio Convertino

If you would like to get the highlights of what each article contains, we recommend to read the special issue introduction written by the editors: Gregorio Convertino, Adam Westerski, Anna De Liddo and Paloma Díaz

Otherwise, if you are just anxious to read the contents straight-away: all articles are available in PDF form online and for free at the JSMO website.

Take note that the idea behind this special issue was to connect with authors working on their promising new research and ongoing applied projects. We wanted to provide support together with feedback for those authors who want to share with the public the preliminary results of their work and engage in a discussion on improvement of their research so far.

Therefore, if you are particularly interested in some study details, have any comments or perhaps would like discuss collaboration – we encourage you to contact the authors directly through contact emails available per each article.

The special issue is an outcome of joint effort of article authors, special issue editors and journal editors (especially Laurie Damianos and Jill Drury). We would like to thank all of them for the work put.

Gi2MO IdeaStream for Drupal 7.x released!

Posted By on July 27, 2014

We are happy to announce another milestone in Gi2MO IdeaStream development. Starting from now on, we give our user base the choice to pick which version of Drupal they prefer to use. Gi2MO IdeaStream supports both 6.x and 7.x with the same core set of Idea Management System functionalities.

Drupal is a popular Content Management System (CMS) which is used by Gi2MO IdeaStream as a base platform. Initially, years ago when we kicked-off our project, IdeaStream was developed for the most popular version of Drupal system at the time – version 6.x. However, since then both IdeaStream and the Drupal platforms have evolved.

In 2011 Drupal had its first 7.x release. The new version update has brought many changes, not only for the users but also in the overall system architecture. This had a profound impact on a lot of open-source modules and the community of developers that contributed earlier to Drupal 6.x.

To this day many of the Drupal 6.x modules have their 7.x versions not yet fully developed, missing a lot of key features or simply in their alpha/beta state with a number of bugs. For this reason, Gi2MO IdeaStream has been a bit stale as far as Drupal 7.x adoption goes.

However, today we would like to go ahead and deliver a version dedicated for Drupal 7.x for those who already require to use the new Drupal version. For us this meant a full rewrite of the entire Gi2MO IdeaStream, some community modules had to be removed, while others replaced with different ones. However, today we are happy to deliver a fully functional IdeaStream version for Drupal 7.x with a complete set of features available before for 6.x users.

If you would like to try the new version, please go to our Apps section for IdeaStream. Since this is the first release for Drupal 7.x, we would be very happy to get any feedback about potential problems or feature requests.

On the other hand, if you are not sure about this update and would like to know more about Drupal 7.x please read below our recommendations.

Should You upgrade/migrate to Drupal 7.x?

For those who are fully aware of Drupal 7.x capabilities and limitations, yet still require to use that version: Gi2MO IdeaStream v7.x-1.8 delivers them all what the 6.x does.

For all the other users: we advise not to upgrade yet and wait for Drupal 7.x independent module community to become as rich as currently 6.x.

The reason for above recommendation is a lot worse state of the community modules for version 7.x. A lot of them (including the ones used by IdeaStream) are heavily under-development, constantly changing and often do not have all features of their old but stable 6.x versions. Therefore, unless you need some specific functionality only available under Drupal 7.x, you will be heavily limited in terms of extendability of your system.

What is new about Drupal 7.x?
In our opinion, from the point of view of Idea Management System, the Drupal 7.x update does not bring huge novelties. The core set of functionalities remains the same.

Still there are some changes in visual interaction and in terms of minor additional functionalities. For a detailed list see the Drupal homepage. We anticipate Drupal 7.x to continue evolving and being updated more than 6.x version in the coming future. It is possible that some of the very new community modules will have their versions only available for Drupal 7.x. We would like IdeaStream to be a good choice for now but also for the future. Therefore, we decided to provide a version for both 6.x and 7.x.

CFP: JSMO Journal Special Issue on on Large-Scale Ideation and Deliberation: Tools and Studies in Organizations

Posted By on February 16, 2014


In a continuous effort to support Idea Management research we would like to promote a Call for Papers for a Special Issue of the Journal of Social Media for Organizations (JSMO).

The issue title is: Large-Scale Ideation and Deliberation: Tools and Studies in Organizations.

The journal has already started accepting submissions and will continue until 1 August 2014 (original submission deadline was extended due to some expressions of interest).

The initiative is lead by organizers of a series of successful Large-Scale Idea Management & Deliberation Systems (LSID) workshops. Following the feedback from the participants of the previous year workshop, the organizers decided to provide this year a different formula to disseminate and share latest research achievements and efforts in the deliberation systems area (including Idea Management Systems).

Although the JSMO journal is accepting reports on studies and research of advanced maturity, this particular special issue is mainly created to provide support and feedback for authors who want to share with the public the preliminary results of their research and engage in a discussion on improvement of their research so far.

The Special Issue is expected to gather a number of extended papers from the previous edition of LSID workshop, however the organizers also invite new original submissions.

Journal Website:

SPECIAL ISSUE IMPORTANT DATES (Update: Deadline Extension)

  • Submission deadline: 1 August, 2014
  • Reviews returned: 31 October, 2014
  • Revised manuscripts due: 28 November, 2014

Social computing research has rapidly advanced during the past decade. Large crowds of people are now able to share knowledge using wikis, blogs, and forums; communicate using social networking platforms; and perform tasks using crowdsourcing platforms. In the meantime organisations have appropriated social computing for their own benefits. Thus, a new frontier for design and research has emerged: designing tools that support large-scale ideation and deliberation as well defined and repeatable processes in organisations and civic communities.

A number of promising applications have been developed for commercial and non-commercial uses, such as Ideastorm, Project 10 to the 100, and the LivingVoters guide. Powerful software support platforms have also appeared (for example, see,,, Many types of organisations, from business to education to government, are seeking out such platforms to include their constituencies in their deliberation processes, and their constituencies increasingly expect such opportunities.

Those Large-Scale Ideation and Deliberation (LSID) platforms, however, face open challenges that include:

  • Overwhelming contribution volumes with large redundancy and variable quality
  • Visualizing and managing large-scale deliberations
  • Summarizing the state and content of deliberation to promote engagement and deepen understating, comparing, prioritising and evaluating ideas, or groups of ideas
  • Generating collective creative solutions
  • Translating proposals into commitment to action
  • Proposing interaction, browsing, and input methods that stimulate participation and substantively empower participants
  • Handling complex problems whose solutions require many interdependent parts
  • Defining, evolving, and applying agreed-upon value criteria among multiple stakeholders

This special issue aims to gather experiences and reports on research done worldwide to cope with the aforementioned problems.

For a full list of suggested research themes and detailed submission guidelines see: Call for Papers published on the JSMO website.

Gi2MO IdeaStream v1.8 released: custom taxonomies, internationalisation support and many more

Posted By on November 2, 2013

Today we are happy to bring you yet another update for our flagship open-source Idea Management System – Gi2MO IdeaStream!

This time the core focus went to improvement for the visual side of IdeaStream and adding some features that make accessing IdeaStream functionality easier. All new updates are present in both our themes: IdeaStream classic and IdeaStream Rainbow.

Additionally, like every major update, the new version is full of fixes and small updates that have been requests since the previous release. Here we would like to highlight two of the major new features:

Ability to add custom taxonomies to the filter bar – the updated theme allows users to filter ideas using any sort of taxonomy defined by the administrator, not only with the IdeaStream predefined Idea Categories taxonomy or Idea Statuses.

IdeaStream custom taxonomy filtering

An example of custom taxonomy filtering with a admin defined taxonomy called ‘Complexity’ (right click and open in new tab/window to view hi-res image).

The configuration settings to setup custom taxonomy can be found in a newly added “IdeaStream Settings” located under “Administer\Site Configuration”. Please keep in mind that only taxonomies assigned to Idea content type can be used as filters. In order to add a new taxonomies go to “Administer\Content Management\Taxonomy”. Apart of setting the taxonomy to use as filter the administrator can use the privileges system to set which users should be able to use the new filter and which not.

In order to accommodate taxonomies of any amount of terms, both the Idea Status and custom taxonomy filters now have drop-down menus that list all terms which did not fit into the filter bar.

Another new feature is full internationalisation support. Starting version v1.8 IdeaStream supports Drupal standardised approach to multi-lingual user interface. Both IdeaStream modules and all themes comply with internationalisation API and allow to provide a translated version of the Idea Management Platform in multiple languages.

IdeaStream multi-lingual interface

Multi-lingual support in IdeaStream – a drop-down box can be used to select interface language. (right click and open in new tab/window to view hi-res image).

The tutorial how to setup a multi-lingual up and running in included in the release package, in the install.txt. The file also includes a full list of all fixes and smaller additions in version v1.8. You can grab the newest installation package from the Gi2MO apps page for IdeaStream.

We hope you enjoy the new release and await any sort of feedback or requests for future additions!

Figure out your ideas: introducing Cluster Analysis in IdeaStream Analytics v1.7 release

Posted By on August 7, 2013

Following the past updates for our open-source Idea Management System IdeaStream, today we have some new features for the data analytics module that delivers insights into statistics and various analyses about ideas – IdeaStream Analytics.

The big new addition is called Cluster Analysis and allows to automatically group ideas based on similarities in term patterns and contextual information. For example: analysis of tags, how frequently are they assigned to ideas, if there are any typical groups of tags used together and how are they different from each other.

The key part is the contextual analysis that not only leads to grouping ideas with similar terms but also allows to highlight how particular group is different from the remaining ideas in other groups.

The Cluster Analysis starts to shine in systems of hundreds or even thousands of ideas, where it is difficult to understand the theme of gathered ideas and community preferences. Currently, we implemented 5 different types of analyses: tag, category, frequent keywords (taken from the Drupal full-text search index), Gi2MO Types characteristics (fixed vocabulary describing innovation types) and Gi2MO Links relationships (supplied by the IdeaStream Similarity module).

ubuntu brainstorm cluster analysis

Cluster Analysis of Gi2MO Types annotations run for Ubuntu BrainStorm dataset (right click and open in new tab/window to view hi-res image).

To understand how it all works – let’s see a simple example of an mockup system with ideas for a supermarket. The picture below shows three groups detected based on cluster analysis of the dataset. The first group appears to be generic fruit ideas, the second group are ideas about fruits of a particular kind (peaches), while the third are ideas about vegetables being onions specifically. This already gives a nice overview of the entire system but further insights show that although generic fruit ideas are favoured by the reviewers and get accepted more often (workflow analysis), the detailed ideas about peaches win the community by a significant degree (top amount of comment and comment per idea ratio).

ubuntu brainstorm cluster analysis

Explanation of metrics and an example of Cluster Analysis based on Tags.

To aid such rapid analysis of clusters IdeaStream Analytics delivers some calculations and highlights about all clusters. Firstly, we output the theme for each cluster: a full list terms used in those ideas ordered according to use frequency but also highlighted in bold if the term was detected as distinctive for the group in comparison to other groups. Furthermore, each group is described by idea count, comment count etc. supplied with indicators if the group has the top or minimal value in comparison to other clusters.

Under the hood all of this is implemented using Singular Value Decomposition (SVD) used in a similar way as in an algorithm called Latent Semantic Analysis (LSA). In short, SVD allows to replace idea term annotations with new concepts that represent combinations of old terms, thus simplifying the analysis of idea similarity. Furthermore, SVD output allows to project terms and ideas into the same multi-dimensional space – in practice this allows us to draw a scatter plot to observe semantic distances between ideas and terms visually.

Furthermore, on top of SVD, IdeaStream Analytics uses an unsupervised clustering algorithm called k-Means to automatically group the similar ideas together. Also, to make this meaningful for Idea Management, we add a number of custom calculations to deliver some interesting insights and analytics about the discovered idea groups.

The drawback of the entire solution is that it’s quite hungry for memory and computational power. As a result, the current implementation allows a number of settings to limit the amount of terms analysed and blacklist some unwanted terms (specially useful for keyword analysis that often will have many unwanted words).

To check all this in action go to the apps section for IdeaStream Analytics, download the version and find out yourself!

Since this is a first release of this feature we welcome any feedback and information about its use in practice (e.g. which statistics are missing, how to better describe cluster theme or any sort of complaints).

CFP: Large-Scale Idea Management & Deliberation Systems (LSID 2013)

Posted By on April 17, 2013


Rather than introducing new publications ourselves, this time Gi2MO is joining the effort to stimulate Idea Management research in general! We are happy to announce a Call for Papers for the Workshop on Large-Scale Idea Management & Deliberation Systems (LSID 2013).

Aside of publishing new achievements in the area, the primary aim of the workshop is to be a networking event to start new collaborations. Therefore, aside of typical paper presentations expect organised networking sessions and discussions.

Following the successful formula of the previous workshop editions, all the organisers are going to attend the event, so expect this to be a good opportunity to meet a passionate group of people who work and influence research on large-scale deliberation systems and communities.

Workshop Website:
Twitter Hashtag: #lsdelib
Contact Email:


Held in conjunction with C&T 2013 Conference in Munich, Germany, on June 29, 2013

The workshop aims to assemble a diverse set of participants with an interest in studying or building systems for large-scale ideation and deliberation in business or civic settings. Aside of presenting new work in the area, the goal of the workshop is to enable a multi-disciplinary discussion about the key research questions and related themes underlying the design, deployment, and evaluation of LSID platforms in real world contexts. Therefore, in addition to presentations, the workshop will involve networking activities of all workshop participants in a series of organised discussions on the future developments of deliberation systems and managing collaboration for future joint projects.

The research issues related to workshop area can be summarised by the following problems:

  • How can we facilitate interaction of large communities ?
  • How can we organise information stored in deliberation systems and enable to utilise this data in an efficient way?
  • How can we maintain sustainability of deliberation platforms and stimulate impact of discussions and ideas?

The LSID Workshop invites researchers, engineers, software developers to present their research and works in the field of idea management and deliberation systems. Papers may deal with methods, models, case studies, practical experiences and technologies.

For full CFP see:


  • Gregorio Convertino, Xerox Research Centre Europe (XRCE), France
  • Mark Klein, MIT Center for Collective Intelligence, Cambridge, MA, USA
  • Anna De Liddo, Open University, UK
  • Adam Westerski, Universidad Politecnica de Madrid, Spain
  • Paloma Diaz Perez, Universidad Carlos III, Spain
  • Manas Hardas, Spigit, USA
  • Lu Xiao, University of Western Ontario, Canada
  • Claudio Bartolini, HP Labs, USA
  • Josh Folk, IdeaScale, Washington, D.C.

Faces of Idea Management: Gi2MO IdeaStream redesigns in various case studdies

Posted By on March 11, 2013

Our open source Idea Management System – Gi2MO IdeaStream is built on top of a platform called Drupal. Drupal is a Content Management System (CMS) that delivers huge flexibility in terms of looks (themes) and functionality (modules).

Having deployed IdeaStream in a number of organisations, we would like to highlight how easily and to what degree IdeaStream can be customised to fit into variety of use cases. For this goal we will use a few examples.

1. ETSIT IdeasWeb – student design competition
First up is a very basic scenario: IdeaStream was used at the ETSIT Telecommunication school of the Universidad Politecnica de Madrid to organize a contest for choosing a new design of the school website. The goal for us here was to quickly deploy the system to let students vote as soon as possible, yet to allow them to see the proposed designs at the frontpage immediately when it loads.


Front page of the ETSIT IdeasWeb competition.

2. ELLIOT – civic innovation in green technologies
Next example comes from INRIA institute. The INRIA researchers used IdeaStream as part of their experiments with civic innovation in an EU funded project called Elliot. In one of their case studies on green technologies, IdeaStream looks was completely overhauled to fit project theme. In comparison to the original theme Elliot version new looks is more squeezed allowing to see more ideas in one go.


Modified IdeaStream to fit the green theme of Elliot project.

3. IdeaStream Rainbow
Finally, in our own experiments, we tested how far theming could be pushed. For this goal, we created a more colourful theme that contrasts with the clean enterprise look of the original IdeaStream theme. The goal here was to go toward candy looks of Web 2.0 websites but still to maintain some of the seriousness of Idea Management platforms.


Idea Contests page of an alternative theme for IdeaStream that presents a more vivid and colourful face of the IMS.

If you would like to see for yourself how this theme works in action, you can do just that by downloading the newest version of Gi2MO IdeaStream! Today, we are happy to release IdeaStream v1.7 that includes the new theme called IdeaStream Rainbow and some minor bug fixes. Additionally, having tested IdeaStream with a number of organisations over the past years, we are happy to finally move out from alpha and release it as a stable build!

As usual for download links see the Gi2MO apps section.

If you would like to customise IdeaStream to fit your own use case let us know, we will be happy to help! Optionally, if you already done it and would like to share you own experiments with open-source community of IdeaStream – give us a shout and we will be happy to highlight it here.

Idea Relationship Visualisation with Gi2MO technologies

Posted By on March 1, 2013

Some time ago we introduced a new module for IdeaStream called Similarity. The module delivered a number of features that enabled users as well as moderators to mark relationships between ideas automatically detected as similar.

Today, we would like to share a research prototype that visualises this relationship data and provides some basic statistics on how ideas are connected to each other.

The Gi2MO Relationship Visualizer allows to filter relationship views by type and filter out connections for a single idea. Additionally, the demonstrator allows to have a peak at some of the relationship statistics such as: number of ideas connected with relationships, number of relationships, max/min/average amount of relationships per idea.


Gi2MO Relationship Visualizer showing ‘Alternative Idea’ relationships detected in Ubuntu BrainStorm.

The Gi2MO Relationship Visualizer can work with any system as long as it allows to export IMS data into RDF/XML following our Gi2MO Ontology guidelines. For instance, in IdeaStream Idea Management platform, this can be achieved with our RDFme module.

The goal of this prototype is to give some insight into idea relationships in Idea Management System and present this information in an accessible form. The prototype has been created by Pablo Moncada using JavaScript and some PHP with ARC2 library for backend processing. This work was done to demonstrate research results on idea relationships hierarchy Gi2MO Links for a spanish funded project THOFU on hotel innovation.

As usual, the complete source code and overview of the software can be found in related Gi2MO Apps subsection. Optionally, you can have a quick peak at a screencast below, recorded to demo the main features of the Visualizer.

Upcoming thesis defence on Semantic Technologies in Idea Management

Posted By on February 6, 2013


We are happy to announce a presentation that will take place at Universidad Politécnica de Madrid, School of Telecommunication, Madrid, Spain. The talk will sum up most of the research done so far in the Gi2MO Project in context of scientific activities of the Intelligent Systems Group.

The presentation is going to focus on research aspects of building four components that we have delivered across the years:

  • Gi2MO Ontology – interoperability and data portability in Idea Management Systems
  • Marl: Linked Opinions – use of opinion mining in Idea Management for automatic idea ranking and linking opinions
  • Gi2MO Types – manual/automatic idea annotation with domain independent characteristics for building idea and community performance metrics
  • Gi2MO Links – use of idea relationship taxonomy for clustering of ideas

The talk entitled “Semantic Technologies in Idea Management Systems: A Model for Interoperability, Linking and Filtering” will be given by Adam Westerski as part of his PhD defence at 17:00, 20th of February, 2013 in Salon de Grados, ETSIT UPM, Building A.

The thesis is already available for download (hires or lores) and can be found in our Gi2MO Docs section, with the slides to follow shortly after the presentation.

Update: The thesis defence has successfully finished (passed with honors) so, as promised, we share the presentation slides.