oliverluk

Interesting, thanks for the heads up. I will implement the following safeguard:

* Known: Paper DOI, paper PMID, author last name, author initials

* Get connected ORCIDs based on the DOI / PMIDs

* Check if the known last name matches the last name of the ORCID profile (also include the "Also known as" section of the profile)

This may lead to some false negatives (for example in case of name changes that were not properly recorded) but if I can reduce the amount of manual lookups to a number below 100, it's already a win.

Thanks a lot for the detailed response! I was indeed not aware of the scope of the problem and the fact that it has its own Wikipedia page.

Also many thanks making me aware of ORCID (together with "DamonHD"). After doing some digging I found ORCID API endpoints which are able to resolve DOIs and PMIDs to ORCID profiles, which is great.

I will take a closer look at the "disambiguation" project you linked to and will see what approach I can take for reliably resolving email addresses to first names (while filtering out non-personal email addresses).

That being said, I fear that resolving non-ORCID + non-email authors using the SerpApi + LLM approach I described in my initial post is still the best shot I currently have.

The process described by "ailef" is exactly what I have in mind. I manually tried the following prompt (which surely has a lot of room for improvement) in ChatGPT (GPT 4.0) with a few examples and got exactly what I needed.

Prompt:

Disambiguate the initials of "X Y Lastname" based on the following JSON input. Do not conduct a web search. Return the full name and the link to the reference as a JSON object with the keys "first_name", "last_name", "link_to_reference". Return "not found" in case you are not able to disambiguate the initials. Do not return anything else.

JSON input:

[the array scoped under the key "organic_results" of the JSON object SerpApi returns when searching for "{author_last_name_with_initials} full name {institute_name}" using Google]

I agree and I'm not too happy about this approach as well. Still, this appears to be my best shot for the authors without ORCIDs. I will try to increase the accuracy through guardrails, good prompting and occasional spot checks.

Many thanks for the hint! After doing some digging I found ORCID API endpoints which are able to resolve DOIs and PMIDs to ORCID profiles. While not all of the authors of the papers I checked are included (because some obviously do not have ORCIDs), this will likely solve the issue for a good chunk of the authors. Great!

I already tried this route (using the DOI), unfortunately, I was not able to get the first names of the authors this way. Example: https://search.crossref.org/search/works?q=10.1111%2Fanae.14...

Guess this argument can also be made the other way round - larger communities > more interaction and knowledge transfer > harder drill bits. I doubt that human progress can be boiled down to a few factors but has to be seen as a chaotic system with each node influencing every other.

Great video! And you could give Weavly a try - we're an easy online video editor and support Vine since Wednesday this week! Here is great video mashup made with scenes taken during the first week of Vine: http://weavly.com/watch/k1bhGlloSwb

Hi Hamai, yes, you're right. We had a close look at the TOS of all the sources we're currently supporting and offering the possibility to use only the sound of a YouTube video is one of the things we're not allowed to do.

Hi Steren, yes, we're currently working on a pure HTML5 version of Weavly.

We’ve made the decision to start with a Flash version first as embedding an application like the Weavly player in the Facebook stream is currently only possible by using Flash - and we wanted to be present on Facebook from day one. But getting the HTML5 version finished is our next target and we should be able to publish it within the coming weeks.