I work on big data in CSV format, prior to further analyzes. I use Data cleaning through OpenRefine to check wether or not words has been correctly spelled. I found out the issue that my word "rejuvenator" has different column with "rejuvenators". Simply, I removed "s" from the column "rejuvenators". Then I perform recluster and edit. But, the word still counting as different word. Does Openrefine was unable to notice that "rejuvenator" was different from "rejuvenators"?
I dont have any issue if Openrefine work was detected from same column for example "rejuvenator" and "Rejuvenator" but in my case openrefine detected in two different column. How to fix it?
OpenRefine’s clustering and similarity detection typically work within a single column at a time, so it may not automatically detect similarities between values in different columns. That is why “rejuvenator” and “rejuvenators” in separate columns are treated as distinct entries.
To address this, you might consider:
Also, check the clustering method settings (like “Key Collision” or “Nearest Neighbor”) and adjust similarity thresholds to better capture minor differences like plurals or typos.
If you provide more details about your dataset structure, I’d be happy to suggest more tailored solutions
- Badges
- Science topic
- Similar topics
- Computer Science
- Research Topics