Direct answers for search queries in the long tail
Abstract
Web search engines now offer more than ranked results. Queries on topics like weather, definitions, and movies may return inline results called answers that can resolve a searcher's information need without any additional interaction. Despite the usefulness of answers, they are limited to popular needs because each answer type is manually authored. To extend the reach of answers to thousands of new information needs, we introduce Tail Answers: a large collection of direct answers that are unpopular individually, but together address a large proportion of search traffic. These answers cover long-tail needs such as the average body temperature for a dog, substitutes for molasses, and the keyboard shortcut for a right-click. We introduce a combination of search log mining and paid crowdsourcing techniques to create Tail Answers. A user study with 361 participants suggests that Tail Answers significantly improved users' subjective ratings of search quality and their ability to solve needs without clicking through to a result. Our findings suggest that search engines can be extended to directly respond to a large new class of queries.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The VA's limitations in handling less common or unique edge queries bear semblance to the 'long tail problem' in information retrieval.
“this bears semblance to the 'long tail problem' in information retrieval [4].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [4]
Despite their individual infrequency, long-tail queries dominate overall.
“Despite their individual infrequency, these long-tail queries dominate overall [4].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [4]
Cites
What are you looking for?: an eye-tracking study of information usage in web search
Cutrell, E., & Guan, Z. (2007) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1240624.1240690 · Cited by 460 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Twitch crowdsourcing: crowd contributions in short bursts of time
Vaish, R., Wyngarden, K., Chen, J., Cheung, B., & Bernstein, M. S. (2014) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/2556288.2556996 · Cited by 95 · see citing works
Self-citationMahmood, A., Wang, J., & Huang, C.-M. (2026) · ACM Transactions on Accessible Computing · doi:10.1145/3796236 · Cited by 6 · see citing works
“…( 64.29% error rate) and historical information ( 60.00% ) or those that did not fit into any category ( 44.74% )—had higher error rates, highlighting the VA’s limitations in handling less common or unique edge queries; this bears semblance to the “long tail problem” in information retrieval [6].”
Influential
- Authors
- Bernstein, M. S., Teevan, J., Dumais, S., Liebling, D., & Horvitz, E.
- Affiliations
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- Microsoft (United States) (US)
- Venue
- Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2012-05-05
- Pages
- 237-246
- OpenAlex
- W2123958332
- Cited by
- 97
- References
- 1
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 2 · 2023: 3 · 2022: 5 · 2021: 11 · 2020: 4 · 2019: 6 · 2018: 9 · 2017: 10 · 2016: 18 · 2015: 3 · 2014: 14 · 2013: 8 · 2012: 2
- FWCI
- 6.79
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Information Systems › Expert finding and Q&A systems
- Physical Sciences › Computer Science › Information Systems › Web Data Mining and Analysis
- Keywords
- long-tail queries, search quality, information needs, user study
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
