High-speed idea filtering with the bag of lemons

Klein, Mark; Garcia, Ana Cristina Bicharra

doi:10.1016/j.dss.2015.06.005

Cited by 56 publications

(35 citation statements)

References 47 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, raters can also use these ratings instead of relying on their judgment process as a way to decrease effort they apply in the rating process. As much as the number of likes can help raters make their choices, the crowd might have a limited ability to identify an idea's true quality (Klein & Garcia, 2015). Therefore, raters who have a higher tendency to follow the crowd might rely too much on the crowd's opinion and be misled, which can result in their making less accurate choices.…”

Section: Hypotheses Developmentmentioning

confidence: 99%

“…Contest organizers use convergence platforms to distribute the large number of generated ideas among (crowd) raters so that they can independently evaluate ideas (Benbasat, 2010;Germonprez, Hess, Kacmar, & Lee, 2008;Zhang et al, 2002). Related work on platform design for idea convergence provides relevant insights into effective rating systems for idea evaluation (Blohm, Riedl, Füller, & Leimeister, 2016;Klein & Garcia, 2015). However, convergence requires a high cognitive load required from raters (Kolfschoten & Brazier, 2013) when reading, evaluating, and choosing ideas.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Designing idea convergence platforms: The role of decomposition of information load to nudge raters towards accurate choices

Walser¹,

Seeber²,

Maier³

2019

THCI

View full text Add to dashboard Cite

Innovation contests offer organizations the opportunity to source innovative ideas to achieve competitive advantage. However, raters cannot easily converge on the most promising ideas because they can easily feel overwhelmed by the high number of generated ideas. Further, information overload will likely impair raters' decision-making processes and how well they can accurately distinguish good from bad ideas. Digital nudging may counteract this convergence challenge via user interface elements to change how information is presented to users. To design a digital nudge in a convergence platform to effectively nudge raters towards improved choice accuracy, one needs to understand the decision-making processes associated with the convergence task. Considering this goal, we conducted an online experiment in which 190 participants eliminated the least promising ideas in presentation modes with either a high (two ideas/screen) or low (30 ideas/screen) decomposition of information load. Our findings suggest that convergence platforms with a high decomposition of information load help raters make more accurate choices. The extent of elimination and revision decisions raters make partially explained this effect. However, these paradoxical mediation effects depended on whether raters showed a high or low tendency to follow the crowd's opinion. Our findings add to the growing academic knowledge base on idea-selection processes and how one can design convergence platforms with digital nudges to help raters deal with their cognitive constraints and ensure successful convergence.

show abstract

Section: Hypotheses Developmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Designing idea convergence platforms: The role of decomposition of information load to nudge raters towards accurate choices

Walser¹,

Seeber²,

Maier³

2019

THCI

View full text Add to dashboard Cite

show abstract

“…As noted in the introduction, large-scale ideation systems typically do not live up to their promise in practice: they tend to collect large numbers of redundant and shallow ideas of variable quality [2,22,40]. The emerging literature on creative cognition and creativity support tools has identified a number of creativity-enhancing interventions that can significantly improve the performance of large-scale ideation systems by improving individual creativity and/or enhancing collaboration capabilities.…”

Section: Creativity Enhancing Interventionsmentioning

confidence: 99%

“…The promise of these online communities is that participants will benefit from exposure to ideas of others and, thus inspired, will generate better ideas than they would have otherwise. In practice, however, crowd innovation challenges result in large quantities of simple, mundane and repetitive ideas [2,22,40]. Consequently, many organizations have come to see crowd innovation platforms more as marketing gimmicks that energize their customers or constituents, rather than real sources of innovation.…”

Section: Introductionmentioning

confidence: 99%

IdeaHound

Siangliulue

Chan

Dow

et al. 2016

Proceedings of the 29th Annual Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

Prior work on creativity support tools demonstrates how a computational semantic model of a solution space can enable interventions that substantially improve the number, quality and diversity of ideas. However, automated semantic modeling often falls short when people contribute short text snippets or sketches. Innovation platforms can employ humans to provide semantic judgments to construct a semantic model, but this relies on external workers completing a large number of tedious micro tasks. This requirement threatens both accuracy (external workers may lack expertise and context to make accurate semantic judgments) and scalability (external workers are costly). In this paper, we introduce IDEAHOUND, an ideation system that seamlessly integrates the task of defining semantic relationships among ideas into the primary task of idea generation. The system combines implicit human actions with machine learning to create a computational semantic model of the emerging solution space. The integrated nature of these judgments allows IDEAHOUND to leverage the expertise and efforts of participants who are already motivated to contribute to idea generation, overcoming the issues of scalability inherent to existing approaches. Our results show that participants were equally willing to use (and just as productive using) IDEAHOUND compared to a conventional platform that did not require organizing ideas. Our integrated crowdsourcing approach also creates a more accurate semantic model than an existing crowdsourced approach (performed by external crowds). We demonstrate how this model enables helpful creative interventions: providing diverse inspirational examples, providing similar ideas for a given idea and providing a visual overview of the solution space.

show abstract

“…[21] proposed a classification of filtering techniques over several cases. [21] pointed out the work with the management of ideas and creativity is not directly linked to large volumes of information, therefore the attention in the present research has been focused on collaborative filtering, since the participants are mainly human who select the ideas and classify them contributing to the development of their creativity.…”

Section: Introductionmentioning

confidence: 99%

The ICT enhancing the creativity through collective intelligence

Meza¹,

Ortiz²,

Román³

et al. 2017

EAI Endorsed Transactions on e-Learning

View full text Add to dashboard Cite

Nowadays, society and organizations face an accelerated innovation that requires of professionals with new skills and attitudes, especially those related to collective creativity. However, educational environments are slowly integrating emerging paradigms limiting the contribution to the development of key skills related to innovation. Multiple investigations claim that teachers have conservative attitudes toward collaborative schemes, while employers generally recognize the effectiveness of creativity at work. Management of ideas is the core of creativity in innovation processes in the industry and in production and service management. This depends largely on the collective work and individual social skills, as well as on the capabilities that information technology and communication (ICT) provide. This article presents a process of collective ideas refinement (CIR) and combines paradigms of swarm creativity and social skills as a means to capture the participants' emotions.

show abstract

High-speed idea filtering with the bag of lemons

Abstract: High-speed idea filtering with the bag of lemons The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters.

Cited by 56 publications

References 47 publications

Designing idea convergence platforms: The role of decomposition of information load to nudge raters towards accurate choices

Designing idea convergence platforms: The role of decomposition of information load to nudge raters towards accurate choices

IdeaHound

The ICT enhancing the creativity through collective intelligence

Contact Info

Product

Resources

About