I have delayed my weekly reads due to vacation / travels abroad. Nevertheless, I collected interesting reads from the previous month.
Discoverers in scientific citation data – this research finds that there are a group of researchers who are good at discovering (or citing early) potentially important papers. This reminds me of the book Superforecasting which talks about how some people are better than others in forecasting the future.
Choices and Consequences: Impact of Mobility on Research-Career Capital and Promotion in Business Schools – In a study of 376 professors in European business schools, they find that mobility is useful in building research careers. At the same time, moving too much can also delay promotions.
The Art of the Pivot: How New Ventures Manage Identification Relationships with Stakeholders as They Change Direction – there is so much emphasis these days for startups to be able to pivot. The problem however is that pivoting is not so easy when you have many stakeholders to appease. This research gives insights on how to manage such relationships with important stakeholders when a startup needs to pivot.
Political skills and career success of R&D personnel: a comparative mediation analysis between perceived supervisor support and perceived organisational support – like many things, the technical superiority of an entity (whether it’s a product, firm or an employee) does not guarantee its success. In this study, they look at R&D employees and find that political skills are important for one to get ahead in one’s career.
Collaborative patents and the mobility of knowledge workers – In my field of FBDD, research mobility seems to be one of the most important mechanisms for the knowledge to spread. In this study of the European biotech sector, inventors who were previously located together are found to form collaborations faster.
Taking leaps of faith: Evaluation criteria and resource commitments for early-stage inventions – Researchers use text mining to quantify how technology transfer office evaluate and decide to financially back a new invention. They find that feasibility and desirability (expressed through words used in the examination document) are important for new inventions.
Exploration versus exploitation in technology firms: The role of compensation structure for R&D workforce – people respond to incentives. This study explores how a firm can structure its incentives as a lever to incentivize exploration / exploitation. In this study, the researchers find that firms with ” higher-powered tournament incentives in vertical compensation structure report higher fraction of innovation directed towards exploration”
Aligning technology and institutional readiness: the adoption of
innovation – It’s always exciting to explore how big firms adopt innovation. While technological readiness is important, researchers in this paper introduce that it should be complemented with the idea of institutional readiness.
Team efficiency and network structure: The case of professional League of Legends – with the amount of data generated by Esports, we should expect more management insights coming from them. In this study, they look at the effect of team interactions/centrality on team performance.
For the next month, I’ll be at the University of Cambridge to conduct a study on how fragment-based drug discovery thrived in the area.
The Legitimacy Threshold Revisited: How Prior Successes and Failures Spill Over to Other Endeavors on Kickstarter – previous outcomes in Kickstarter affect future crowdfunding efforts by “encouraging audiences to repeatedly support other related endeavors or by discouraging them from doing so.”
The Time Efficiency Gain in Sharing and Reuse of Research Data – sharing research data can yield to efficiency gains to the scientific community
Does combining different types of collaboration always benefit firms? Collaboration, complementarity and product innovation in Norway – conventional thinking dictates that firms should collaborate as much as they can to increase the chances of innovation occurring. This study however finds that pursuing all types of collaborations (in this case, scientific and supply chain) might not be useful all the time as these might interact and may negatively impact innovation.
It’s in the Mix: How Firms Configure Resource Mobilization for New Product Success – networks are always fascinating. Here, they look at the new product development through a network perspective.
Improving the peer review process: a proposed market system – Currently, reviewers do not receive any compensation given the amount of work they have to do. This is bad for science as well because papers do not get reviewed properly/fast enough. Creating a market system for the review process for better incentivization of both authors and reviewers might improve the process.
Federal funding of doctoral recipients: What can be learned from linked data – New datasets are always exciting. Researchers in this study propose linking a huge dataset on university payrolls with another huge survey about PhD graduates. It would be interesting to see how other researchers will use data to understand innovation, basic research, career development to name a few.
Universities and open innovation: the determinants of network centrality – Universities that are located centrally in their university-industry networks are also in better position to generate spinoffs and conduct projects with external funding.
Browsing the Grad school subreddit, there was a post by the user EvilCalamari about creating a science lab version of Kitchen Nightmares. If you are not familiar with this, it’s a reality tv show by the famous chef Gordon Ramsey where he goes to failing restaurants and shreds these establishments’ bad practices. The show is quite educational as it shows the common mistakes that would-be restaurateurs make – from dirty kitchens to inefficient systems.
With so many controversies in the scientific world, there are countless settings that such a show could explore. There’s sloppy science involving incorrect citations in papers and labs that are so badly managed that it would sound OSHA’s alarms. There’s of course deliberate misconduct from fabricating data to plagiarisms.
The question though is who can be the Gordon Ramsay of the scientific world?
This week seems to be a special one for the field of entrepreneurship, with some publications on the merits of studying it from an academic perspective such as this one A wakeup call for the field of entrepreneurship and its evaluators
Has the Concept of Opportunities Been Fruitful in the Field of Entrepreneurship? – In line with the previous one, this reflects on the concept of opportunities which has always been in the same conversation with entrepreneurship. I have not been able to access the article despite various searchers but I’m sure that it touches on the perennial question on whether opportunities are created or discovered. I find this discussion fascinating because by itself, entrepreneurship research is already too scholarly. Going one step backwards and reflecting on such philosophical questions, perhaps pushes this even further.
Firm Strategic Behavior and the Measurement of Knowledge Flows with Patent Citations – Ever since I got into bibliometrics, citations have been fascinating. Instead of just a measure of paper’s worth and knowledge flow, citations also reflect other subtle things such as informal ties, cliques and prestige. In this paper, the researchers looked at patent citations and explores how it does not only reflect knowledge flow but also other other factors including firm strategy and intellectual property regime.
Predicting citation counts based on deep neural network learning techniques – in the theme apply neural networks to everything, in this paper, the researchers aimed to predict citation counts of papers. This makes me wonder whether we could reverse the process one day and design an AI that can output papers according to an input citation count.
Optimal Distinctiveness, Strategic Categorization, and Product Market Entry on the Google Play App Platform – optimal distinctiveness is really taking the management literature by storm. It will probably be the next open innovation or absorptive capacity with the growth in publications about it such as this one looking at app success.
Recently, there was an article in Scientometrics about main path analysis by Liu et al. It’s supposed to help trace the development path of a scientific or technological field. Before hearing this, I was just being content with the capabilities of CitNetExplorer in showing the trends in my field of interest. However, after reading the technique’s capabilities. I was quite intrigued as it may make analyzing the overarching trend in a field of interest simpler to visualize. The only problem is that there is really no tutorial on how to do it. The only thing I found was this youtube video using Pajek, which honestly was not very informative. To add to that, I did not have experience with Pajek, and with its very intimidating interface, I really had to tinker with it. Nonetheless, after playing with it, I hacked my way into generating my own main path analysis plots.
In the following, I will explain the process. Note that I do not have much experience with Pajek so there might be easier ways to do it.
The workflow I engineered was this (more explanation in the coming days):
- Download articles from Web of Knowledge
- Import articles to CitNetExplorer
- Export the citation network file from CitNetExplorer
- Reformat the file into a Pajek .net file
- Import Pajek net file to Pajek
- Run Network -> Acyclic Network -> Create Weighted Network + Vector -> Trasversal Weights -> Search Path Link Count (SPLC). Note that you can choose others weights such as SPC and SPNP. In the article above however, they recommended SPLC as they said that it somehow reflects how knowledge diffuse in real life.
- Run Network -> Acyclic Network -> Create (Sub)Network -> Main Paths -> Global Search -> Key-Route
- Enter an arbitrary number of routes. I tried 1-50.
- Run Draw -> Network
- Run Layout -> Kamada Kawai -> Fix first and last vertex
This is a sample map for the field of Fragment-based drug discovery.
[In progress. Updates in the coming days]
The age at which Noble Prize research is conducted – Spoiler alert: It’s 44
Zero impact: a large-scale study of uncitedness – It’s common knowledge that a large number of scientific articles do not get cited, from this article around 20-30%. This article breaks down the level of uncitedness per subject and article type. This begs the question, if a tree falls in a forest and no one is around to hear it, does it make a sound?
How optimal distinctiveness affects new ventures’ failure risk: A contingency perspective – I really am fond of this topic optimal distinctiveness. In this study, they looked at metal bands and how much distinct they can be with their mix of sub-genres. They show that optimal distinctiveness is relevant to the failure risk of new ventures.
Is Elsevier helping or hurting scientific progress? – Fascinating podcast opening a dialogue between a scientist in Elsevier and an advocate of open science. I like how the host Julia and the participants tried to see each other’ perspective and not only discredit each other. Personally, I adore Elsevier and how it is moving towards more of a service company than a traditional journal publishing one.
The past week there has been a lot of fuss over the release of a language model by OpenAI which was supposed to be the most advanced yet. There is a lot of discussion online too because of the team’s decision to not release the full version of the model, afraid that it will be misused by Russian trolls, Chinese spies or whatever. Nonetheless, the partial model has been available for researchers to tinker with. To make things more convenient, there has also been an online implementation to skip the troubles of having to install the model on my computer.
I played with it to try to find out if it would help me write my doctoral dissertation. Maybe not, but at least give me some inspiration. These are my queries followed by the model’s continuation:
Prompt: Absorptive capacity is important for firms to gain competitive advantage.
A high birth rate reduces labor size relative to that in the United States (approximately 2.5 births per woman per 100 that would be generated in the United States in 2025) by the same method that causes individual WL to lag the rest of the world as a comparable technology (James and Wilcox 2005; Steuber and Turnbull 2006). Moreover, this concept establishes that WL may very well be a competitive advantage in conduct metrics secondary to WL. Thus, in conclusion, an incomplete equilibrium system often poses the problem of generating the next big PBE, ready for limiting these situations…
Prompt: To create disruptive innovations, companies should…
not work in the present day and if they do: “We’re not picking those lines for half-measures. ” Trust Poopmakers, Congress The hard law enforcement obligation imposed by the U. S. government on startups and small businesses should be absolute, followed by the next step. However, the United States should not violate copyright as being without regard to collateral damage and even have some credentials as a custodian of such equivalent works. Counterproductive courts should inquire into the bill from both sides and pass amendments for the immediate reporting of the U. S. to the American people…
The results have been disappointing unfortunately. We are not yet at a point that doctoral students can be replaced by actual robot slaves.