scholarly journals Creative exploration using topic-based bisociative networks

2018 ◽  
Vol 4 ◽  
Author(s):  
Faez Ahmed ◽  
Mark Fuge
Keyword(s):  
Idea Generation ◽  
Information Network ◽  
Large Collection ◽  
Computational Framework ◽  
Conceptual Similarity ◽  
Cross Domain ◽  
Unstructured Text ◽  
Collaborative Community ◽  
Creative Solutions ◽  
Multiple Domains

Bisociative knowledge discovery is an approach that combines elements from two or more ‘incompatible’ domains to generate creative solutions and insight. Inspired by Koestler’s notion of bisociation, in this paper we propose a computational framework for the discovery of new connections between domains to promote creative discovery and inspiration in design. Specifically, we propose using topic models on a large collection of unstructured text ideas from multiple domains to discover creative sources of inspiration. We use these topics to generate a Bisociative Information Network – a graph that captures conceptual similarity between ideas – that helps designers find creative links within that network. Using a dataset of thousands of ideas from OpenIDEO, an online collaborative community, our results show usefulness of representing conceptual bridges through collections of words (topics) in finding cross-domain inspiration. We show that the discovered links between domains, whether presented on their own or via ideas they inspired, are perceived to be more novel and can also be used as creative stimuli for new idea generation.

Categorization flexibility and unconventional choices: is life an adventure?

2020 ◽  
Vol 54 (8) ◽  
pp. 1963-1986
Author(s):  
Tilottama G. Chowdhury ◽  
Feisal Murshed
Keyword(s):  
Interactive Effect ◽  
Interactive Effects ◽  
Cognitive Capacity ◽  
Purchase Behavior ◽  
Consumer Decision Making ◽  
Cross Sectional ◽  
Content Type ◽  
Cross Domain ◽  
Multiple Domains

Purpose This paper proposes that categorization flexibility, operationalized as the cognitive capacity that cross-categorizes products in multiple situational categories across multiple domains, might favorably influence a consumer’s evaluation of unconventional options. Design/methodology/approach Experimental research design is used to test the theory. An exploratory study first establishes the effect of categorization flexibility in a non-food domain. Study 1 documents the moderating role of decision domain, showing that the effect works only under low- (vs high-) consequence domain. Studies 2A and 2B further refine the notion by showing that individuals can be primed in a relatively higher categorization flexibility frame of mind. Study 3 demonstrates the interactive effect of categorization flexibility and adventure priming in a high-consequence domain. Study 4 integrates the interactive effects of decisions with low- vs high-consequence, adventure priming and categorization flexibility within a single decision domain of high consequence. Findings Consumers with higher- (vs lower-) categorization flexibility tend to opt for unconventional choices when the decision domain entails low consequences, whereas such a result does not hold under decision domain of high consequences. The categorization flexibility effects in case of low-consequence decision domain holds true even when consumers are primed to be categorization flexible. Furthermore, with additional adventure priming, consumers show an increased preference for unconventional options even under a decision domain with high consequence. Research limitations/implications This study could not examine real purchase behavior as results are based on cross-sectional, behavioral intention data. In addition, it did not examine the underlying reason for presence of cross-domain categorization flexibility index. Practical implications The results suggest that stimuli may be tailored to consumers in ways that increase the salience and the perceived attractiveness of unconventional choices. Further, data reinforce the notion of cross-categorical interrelations among different domains, which could be leveraged by marketers. Originality/value This study represents the first documentation of the potential ways by which unconventional product choice might be a function of individuals’ categorization flexibility level across different types of decision domains. The findings yield implications that are novel to both categorization and consumer decision-making literature.

scholarly journals Combining knowledge to generate novelty: a study of disclosed ideas for life science inventions

2017 ◽  
Vol 20 (3) ◽  
pp. 446-462 ◽  
Author(s):  
Taran Thune ◽  
Magnus Gulbrandsen
Keyword(s):  
Life Science ◽  
Idea Generation ◽  
New Product ◽  
Original Data ◽  
Generation Process ◽  
Data Set ◽  
Content Type ◽  
Cross Domain ◽  
Research Activities ◽  
New Ideas

Purpose The purpose of this paper is to investigate how a combination of diverse sources of knowledge is important for generation of new ideas and address how institutional infrastructures and practices support integration of knowledge across organizations in medicine and life sciences. Design/methodology/approach The paper investigates new product ideas that emerge from hospital and university employees, and looks at the extent of interaction between clinical and scientific environments in the idea generation process. The paper utilizes data about all new product ideas within life science that were reported in South-Eastern Norway in 2009-2011, as well as information about the individuals and teams that had been involved in disclosing these ideas. Interviews with inventors have also been carried out. Findings Interaction and integration across scientific and clinical domains are common and important for generating new product ideas. More than half of the disclosed life science ideas in the database come from groups representing multiple institutions with both scientific and clinical units or from individuals with multiple institutional affiliations. The interviews indicate that the infrastructure for cross-domain interaction is well-developed, particularly for research activities, which has a positive effect on invention. Originality/value The paper uses an original data set of invention disclosures and investigates the hospital-science interface, which is a novel setting for studies of inventive activities.

Enriching Topic Coherence on Reviews for Cross-Domain Recommendation

2020 ◽  
Author(s):  
Mala Saraswat ◽  
Shampa Chakraverty
Keyword(s):  
Topic Modeling ◽  
Semantic Analysis ◽  
User Generated Content ◽  
Core Concept ◽  
Semantic Clustering ◽  
Cross Domain ◽  
Semantic Coherence ◽  
Reference Corpus ◽  
Multiple Domains ◽  
Explicit Semantic Analysis

Abstract With the advent of e-commerce sites and social media, users express their preferences and tastes freely through user-generated content such as reviews and comments. In order to promote cross-selling, e-commerce sites such as eBay and Amazon regularly use such inputs from multiple domains and suggest items with which users may be interested. In this paper, we propose a topic coherence-based cross-domain recommender model. The core concept is to use topic modeling to extract topics from user-generated content such as reviews and combine them with reliable semantic coherence techniques to link different domains, using Wikipedia as a reference corpus. We experiment with different topic coherence methods such as pointwise mutual information (PMI) and explicit semantic analysis (ESA). Experimental results presented demonstrate that our approach, using PMI as topic coherence, yields 22.6% and using ESA yields 54.4% higher precision as compared with cross-domain recommender system based on semantic clustering.

The Effects of Elaboration in Creativity Tests as it Pertains to Overall Scores and How it Might Prevent a Person From Thinking of Creative Ideas During the Early Stages of Brainstorming and Idea Generation

2015 ◽  
Author(s):  
Caitlin Dippo ◽  
Barry Kudrowitz
Keyword(s):  
Problem Solving ◽  
Negative Correlation ◽  
Real World ◽  
Idea Generation ◽  
Occurrence Rate ◽  
The Novel ◽  
Strong Negative Correlation ◽  
Relative Occurrence ◽  
Real World Problem ◽  
Creative Solutions

Previous studies have found that the first few ideas we think of for a given prompt are likely to be less original than the later ideas. In this study, 460 participants were given the Alternative Uses Test (AUT) where they were asked to list alternative uses for a paperclip, creating a database of 235 unique answers, each having a relative occurrence rate in that pool. It was found that later responses were significantly more novel than early responses and on average the originality of responses exponentially increased with quantity. A closer look at this data reveals that a person is likely to have a lower overall originality score if he or she has more elaborate responses. 89 of these participants were also given the Abbreviated Torrance Test For Adults (ATTA) and the data from both tests was used to study relationships between elaboration, fluency, and originality. The data from the AUT reveals a strong negative correlation between an individual’s average number of words per response and his or her average originality score. It is hypothesized that people who spend more time writing multiple-word responses have less time to generate many different ideas thus hindering their ability to reach the novel ideas. Similarly, the ATTA reveals that after two extraneous details, elaboration on a drawing will negatively impact fluency and originality scores. This is not to say that elaborate ideas cannot be original, but rather that in time-limited situations, elaboration may hinder the production of original ideas. In applying this to real world problem solving and idea generation, it is suggested that people may prevent themselves from finding creative solutions if too much time is spent on discussing the first few suggested ideas from a brainstorming session. It is suggested that a more effective brainstorming session will delay discussion until a significant number of ideas are generated.

scholarly journals The Essence of Cross-Domain Deterrence

2020 ◽  
pp. 129-158
Author(s):  
Tim Sweijs ◽  
Samuel Zilincik
Keyword(s):  
Theory And Practice ◽  
Grey Zone ◽  
New Wave ◽  
Military Operations ◽  
Deterrence Theory ◽  
Cross Domain ◽  
Multiple Domains ◽  
The Military

AbstractBoth deterrence theory and deterrence practice are evolving to address contemporary strategic challenges. In the military domain, states progressively integrate and synchronise military operations. Outside of it, they exploit grey zone strategies that combine different instruments of influence across multiple domains. These developments are now giving birth to a new wave of thinking about cross domain deterrence (CDD), what it precisely entails, and what favouring conditions are necessary for it to be effective. This chapter situates CDD in the context of today’s challenges, and identifies the prerequisites for these favouring conditions based on a review of a rather diverse body of literature. It finds that one strand of that literature predominantly focuses on practical and technical prerequisites in order for CDD to be effective, leaving the framework of traditional deterrence theory intact. It also finds a second strand that holds that the nature of today’s challenges requires more than mere innovation in application. The ideas about deterrence proposed by this second strand are expanding on common understandings of deterrence to the extent that deterrence is no longer only about fear nor about convincing opponents to refrain from certain behaviour. The conclusion summarises the findings and elaborates their implications for theory and practice.

A Bisociative Design Framework for Knowledge Discovery Across Seemingly Unrelated Product Domains

2012 ◽  
Author(s):  
Conrad S. Tucker ◽  
Sung Woo Kang
Keyword(s):  
Domain Knowledge ◽  
Current Data ◽  
Data Driven ◽  
Design Framework ◽  
Specific Domain ◽  
Cross Domain ◽  
Product Design Process ◽  
Product Domains ◽  
Multiple Domains ◽  
Novel Design

The Bisociative Design framework proposed in this work aims to quantify hidden, previously unknown design synergies/insights across seemingly unrelated product domains. Despite the overabundance of data characterizing the digital age, designers still face tremendous challenges in transforming data into knowledge throughout the design processes. Data driven methodologies play a significant role in the product design process ranging from customer preference modeling to detailed engineering design. Existing data driven methodologies employed in the design community generate mathematical models based on data relating to a specific domain and are therefore constrained in their ability to discover novel design insights beyond the domain itself (I.e., cross domain knowledge). The Bisociative Design framework proposed in this work overcomes the limitations of current data driven design methodologies by decomposing design artifacts into form patterns, function patterns and behavior patterns and then evaluating potential cross-domain design insights through a proposed multidimensional Bisociative Design metric. A hybrid marine model involving multiple domains (capable of flight and marine navigation) is used as a case study to demonstrate the proposed Bisociative Design framework and explain how associations and novel design models can be generated through the discovery of hidden, previously unknown patterns across multiple, unrelated domains.

scholarly journals Cross-Domain Recommendation: An Embedding and Mapping Approach

2017 ◽  
Author(s):  
Tong Man ◽  
Huawei Shen ◽  
Xiaolong Jin ◽  
Xueqi Cheng
Keyword(s):  
State Of The Art ◽  
Mapping Function ◽  
Multi Layer Perceptron ◽  
Data Sparsity ◽  
Domain Specific ◽  
Cross Domain ◽  
Robustness To Noise ◽  
Promising Solution ◽  
High Flexibility ◽  
Multiple Domains

Data sparsity is one of the most challenging problems for recommender systems. One promising solution to this problem is cross-domain recommendation, i.e., leveraging feedbacks or ratings from multiple domains to improve recommendation performance in a collective manner. In this paper, we propose an Embedding and Mapping framework for Cross-Domain Recommendation, called EMCDR. The proposed EMCDR framework distinguishes itself from existing cross-domain recommendation models in two aspects. First, a multi-layer perceptron is used to capture the nonlinear mapping function across domains, which offers high flexibility for learning domain-specific features of entities in each domain. Second, only the entities with sufficient data are used to learn the mapping function, guaranteeing its robustness to noise caused by data sparsity in single domain. Extensive experiments on two cross-domain recommendation scenarios demonstrate that EMCDR significantly outperforms state-of-the-art cross-domain recommendation methods.

Trials of interventions for people with alcohol use disorders

2015 ◽  
Author(s):  
María Elena Medina-Mora ◽  
Sairat Noknoy ◽  
Cheryl Cherpitel ◽  
Tania Real ◽  
Román Pérez Velasco ◽  
...  
Keyword(s):  
Community Care ◽  
Health Workers ◽  
Treatment Gap ◽  
Severe Mental Disorder ◽  
Community Based ◽  
Human Rights Abuse ◽  
Collaborative Community ◽  
Feasible Option ◽  
Persistent Disability ◽  
Multiple Domains

Schizophrenia is a severe mental disorder that causes serious and persistent disability in multiple domains. People with schizophrenia are also often exposed to widespread sigma, discrimination, and human rights abuse. There is a large and persistent treatment gap for people with schizophrenia and their caregivers globally and in LAMIC;To address this gap, emerging observational evidence from LAMIC suggests that a task-sharing strategy involving community health workers (CHWs) is a feasible option for delivering services to people with schizophrenia and their families . However, there is no RCT evidence from LAMIC that such an approach is more effective than usually available care. The community care for people with schizophrenia in India (COPSI) RCT tested the clinical and cost-effectiveness of a collaborative community-based care (CCBC) intervention with usual, facility-based care (FBC). The FBC + CCBC intervention was superior in reducing symptoms and disability associated with schizophrenia and in improving adherence with treatment.

Sign in / Sign up

Export Citation Format

Share Document