The Scenario
The grant-writing office has a roster of 120 potential collaborators for a multi-institution proposal. The lead PI needs each person's current affiliation, h-index, and total citations filled in — in the workbook, not in a separate document — before the internal review call on Friday morning. You inherited the roster. The previous coordinator left no notes on how they sourced this data.
The bad version:
- Search Semantic Scholar for the first name, find the right author record among disambiguation results (three researchers share the same name), click into the profile, copy the affiliation, copy the h-index, switch back to the workbook, paste both.
- Repeat for name 2. Realize the affiliation field on Semantic Scholar is sometimes a department name, sometimes just a university name — inconsistent across profiles.
- By name 25, you've spent two hours and have 95 rows still blank. The PI just asked if it's ready.
The problem isn't the research — it's that nobody should be spending 15 seconds per row multiplied by 120 rows to populate three columns.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It reads the names in column A, resolves each one against Semantic Scholar's author index, and writes the affiliation, h-index, and citation count directly into the adjacent columns.
Here is the prompt for this task:
For every researcher in the Author Name column, find their Semantic Scholar author ID and then retrieve paper count and h-index, adding both to this table in Excel
What You Get
- Columns filled for each researcher: Author ID, H-Index, Paper Count.
- For common names with multiple matches, SheetXAI selects the most-cited author record and notes disambiguation in a comment column if ambiguity was high.
- Rows where no Semantic Scholar profile was found are flagged clearly rather than left blank.
- H-Index arrives as a number — your ranking formula runs immediately.
What If the Data Is Not Quite Ready
The name column contains formatting inconsistencies — some all-caps, some with honorifics
Before searching, normalize each name in the Author Name column by converting to title case and stripping honorifics like Dr. or Prof., then look up each person on Semantic Scholar and fill in their author ID, h-index, and paper count
You already have some Semantic Scholar author IDs and want to skip the name-resolution step for those rows
For rows in the Author Name column where the Author ID column already has a value, use the ID directly to fetch h-index and paper count; for rows where the Author ID is blank, resolve by name — write results into the H-Index and Paper Count columns
You need to join the enriched data against a second worksheet that has institution-level tiers
After filling in affiliation and h-index for each author from Semantic Scholar, look up each affiliation against the Institutions worksheet column A and pull the tier rating from column B into the Tier column of the Authors worksheet
Disambiguate names, enrich, and flag low-h-index candidates in one shot
Search Semantic Scholar for each name in the Author Name column, select the highest-citation match for any ambiguous names, fill in author ID, h-index, and paper count, then flag any researcher with an h-index below 5 as Emerging in a Status column
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook with a column of researcher names. Ask SheetXAI to pull their Semantic Scholar metrics into the adjacent columns — and have the grant proposal roster ready before Friday's call.
See also: Pull Full Publication Lists by Author ID and the Semantic Scholar hub overview.