Abstract | ||
---|---|---|
Many real world analytics problems examine multiple entities or classes that may appear in a corpus. For example, in a customer satisfaction survey analysis there are over 60 categories of (somewhat overlapping) concerns. Each of these is backed by a lexicon of terminology associated with the concern (e.g., “Easy, user friendly process” or ”Process confusing, too many handoffs”). These categories need to be expanded by a subject matter expert as the terminology is not always straight forward (e.g., “handoffs” may also include “ping-pong” and “hot potato” as relevant terms).
But given that Subject Matter Expert time is costly, which of the 60+ lexicons should we expand first? We propose a metric for evaluating an existing set of lexicons and providing guidance on which are likely to benefit most from human-in-the-loop expansion. Using our ranking results we achieved ≈ 4 × improvement in impact when expanding the first few lexicons off our suggested list as compared to a random selection.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3308560.3317305 | Companion Proceedings of The 2019 World Wide Web Conference |
Field | DocType | ISBN |
World Wide Web,Customer satisfaction,Ranking,Terminology,Differential privacy,Information retrieval,Subject-matter expert,Computer science,Lexicon,User Friendly,Analytics | Conference | 978-1-4503-6675-5 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alfredo Alba | 1 | 77 | 9.87 |
Chad DeLuca | 2 | 0 | 0.68 |
Anna Lisa Gentile | 3 | 200 | 26.00 |
Daniel Gruhl | 4 | 2282 | 434.45 |
Linda Kato | 5 | 35 | 5.31 |
Chris Kau | 6 | 10 | 2.40 |
petar ristoski | 7 | 256 | 21.36 |
Steve Welch | 8 | 5 | 3.34 |