Generating novel research ideas using computational intelligence: A case study involving fuel cells and ammonia synthesis
Generating novel research ideas using computational intelligence: A case study involving fuel cells and ammonia synthesis
复制标题
DOI：
10.1016/j.techfore.2017.04.004
复制
发表时间：
2017-07
影响因子：
12
通讯作者：
Takaya Ogawa;Y. Kajikawa
中科院分区：
文献类型：
--
作者：
Takaya Ogawa;Y. Kajikawa
我们提出了一种方法来帮助研究人员利用文献计量学创造新颖的研究想法。不同的研究领域存在不同的概念和技术，当领域足够相似时，两个不同领域的显着组合可以导致新颖研究的发展。我们假设两个不同的研究领域共享大量相似的关键词，将是整合的绝佳候选者。我们结合了链接挖掘和文本挖掘技术来阐明明显、明确的研究集群中隐藏但隐含的机会。为了证明我们方法的有效性，我们对燃料电池和氨合成进行了案例研究。燃料电池是一个快速发展的研究领域，而氨合成则相对成熟。我们的结果成功地提取了一个合理且成熟的研究想法。
We proposed a method to help researchers create novel research ideas using bibliometrics. Different concepts and techniques exist in different research areas, and when the fields are sufficiently similar, a salient combination of two different areas can lead to the development of novel research. We have assumed that two different research areas, sharing a high number of similar keywords, would be excellent candidates for integration. We combined link mining and text mining techniques to elucidate hidden but implicit opportunities among apparent, explicit research clusters. To demonstrate the effectiveness of our approach, we conducted a case study on fuel cells and ammonia synthesis. Fuel cells are a rapidly growing research field, while ammonia synthesis is relatively mature. Our results successfully extracted a plausible and post-mature research idea.