Development and Evaluation of Search Tasks for IIR Experiments using a Cognitive Complexity Framework
The DOI matches its Crossref record; 44 of the 51 references it cites were found in a registry or an index.
Abstract
One of the most challenging aspects of designing interactive information retrieval (IIR) experiments with users is the development of search tasks. We describe an evaluation of 20 search tasks that were designed for use in IIR experiments and developed using a cognitive complexity framework from educational theory. The search tasks represent five levels of cognitive complexity and four topical domains. The tasks were evaluated in the context of a laboratory IIR experiment with 48 participants. Behavioral and self-report data were used to characterize and understand differences among tasks. Results showed more cognitively complex tasks required significantly more search activity from participants (e.g., more queries, clicks, and time to complete). However, participants did not evaluate more cognitively complex tasks as more difficult and were equally satisfied with their performances across tasks. Our work makes four contributions: (1) it adds to what is known about the relationship among task, search behaviors and user experience; (2) it presents a framework for task creation and evaluation; (3) it provides tasks and questionnaires that can be reused by others and (4) it raises questions about findings and assumptions of many recent studies that only use behavioral signals from search logs as evidence for task difficulty and searcher satisfaction, as many of our results directly contradict these findings.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“Search task complexity was shown to affect user behaviour [18].”
From A Mixed-Method Analysis of Text and Audio Search Interfaces with Varying Task Complexity (2020) · cites this paper as [18]
In the citing paper
“Prior research in visual text search has shown that more complex tasks lead to greater levels of search interactivity, for example, through increased clicks, queries, and time on task [18].”
From A Mixed-Method Analysis of Text and Audio Search Interfaces with Varying Task Complexity (2020) · cites this paper as [18]
Citations
Cites
(2001) · Cited by 13,930
Broder, A. (2002) · ACM SIGIR Forum · doi:10.1145/792550.792552 · Cited by 1,944 · cited 1×
“Broder’s [12] task classification was one of the first in the context of Web search and resulted in three categories of tasks: navigational, informational and transactional.”
BackgroundTask Complexity: A Review and Analysis
Campbell, D. J. (1988) · The Academy of Management Review · doi:10.5465/amr.1988.4306775 · Cited by 1,634 · cited 5×
“Using Campbell’s [15] conceptualization of objective task complexity, Remember tasks have the fewest solution paths, the fewest number of solutions or outcomes, the least amount of conflicting interdependencies between paths and the least amount of uncertainty regarding paths, while create tasks have the greatest numb…”
BackgroundMethodResultInfluentialTask complexity affects information seeking and use
Byström, K., & Järvelin, K. (1995) · Information Processing & Management · doi:10.1016/0306-4573(94)00041-z · Cited by 885 · cited 5×
“The tasks can also be related to Byström and Jӓrvelin’s [14] definition of task complexity in that the expected inputs, processes and outcomes become less certain as one moves from Remember to Create tasks.”
BackgroundMethodInfluentialMethods for Evaluating Interactive Information Retrieval Systems with Users
Kelly, D. (2009) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000012 · Cited by 633 · cited 2×
“Those studying IIR have used these collections in studies with research participants, although not without some challenges [23].”
BackgroundSelf-citationExploratory Search: Beyond the Query-Response Paradigm
White, R. W., & Roth, R. A. (2009) · Synthesis lectures on information concepts, retrieval, and services · doi:10.2200/s00174ed1v01y200901icr003 · Cited by 632 · cited 1×
“White and Roth [40] provide a discussion of these types of tasks and situate them in the context of other task types.”
BackgroundThe IIR evaluation model: a framework for evaluation of interactive information retrieval systems
Borlund, P. (2003) · DOAJ (DOAJ: Directory of Open Access Journals) · Cited by 403
Task‐based information searching
Vakkari, P. (2003) · Annual Review of Information Science and Technology · doi:10.1002/aris.1440370110 · Cited by 366 · cited 5×
“In one of the first reviews of task-based information seeking research, Vakkari [38] defines a task as an “activity to be performed in order to accomplish a goal” (p.”
BackgroundInfluentialA faceted approach to conceptualizing tasks in information seeking
Li, Y., & Belkin, N. J. (2008) · Information Processing & Management · doi:10.1016/j.ipm.2008.07.005 · Cited by 336 · cited 8×
“For example, Li and Belkin [28] found that objective task complexity was related to number of queries issued, mean query length, number of pages viewed, and number of sources consulted.”
BackgroundMethodResultInfluentialConceptual framework for tasks in information studies
Byström, K., & Hansen, P. (2005) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.20197 · Cited by 220 · cited 1×
“Byström and Hansen [13] distinguish between a work task and a search task, one or more of which might be conducted to address the work task.”
BackgroundHow does search behavior change as search becomes more difficult?
Aula, A., Khan, R. M., & Guan, Z. (2010) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1753326.1753333 · Cited by 209 · cited 1×
“could not be solved, or solved easily [1, 6].”
BackgroundExploratory Search: Beyond the Query—Response Paradigm
White, R. W., & Roth, R. A. (2009) · Synthesis Lectures on Information Concepts, Retrieval, and Services · doi:10.1007/978-3-031-02260-9 · Cited by 182
Conceptual framework for tasks in information studies
ByströmKatriina, & Hansen, P. (2005) · Journal of the American Society for Information Science and Technology · doi:10.5555/1072003.1072010 · Cited by 178
Allan, J., Croft, B., Moffat, A., & Sanderson, M. (2012) · ACM SIGIR Forum · doi:10.1145/2215676.2215678 · Cited by 176
Using the taxonomy of cognitive learning to model online searching
Jansen, B. J., Booth, D., & Smith, B. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.05.004 · Cited by 164 · cited 2×
“[21] used Anderson and Krathwohl’s taxonomy of educational objectives [3] to create complex search tasks reflecting six types of cognitive processes: remember, understand, apply, analyze, evaluate and create (see Table 1 for definitions).”
BackgroundMethodSearcher’s Assessments of Task Complexity for Web Searching
Bell, D. J., & Ruthven, I. G. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24752-4_5 · Cited by 135 · cited 2×
“For example, Bell and Ruthven [8] used Byström and J ӓ rvelin’s conceptualization to create artificial search tasks with different levels of task complexity and found that objective task complexity as they had manipulated it, was correlated with users’ subjective assessments of complexity.”
BackgroundLet's Stop Pushing the Envelope and Start Addressing It: A Reference Task Agenda for HCI
Whittaker, S., Terveen, L., & Nardi, B. A. (2000) · Human–Computer Interaction · doi:10.1207/s15327051hci1523_2 · Cited by 131 · cited 1×
“There have also been long-standing calls for the development of standardized task sets, reference tasks and sharable tasks that can be used in information search studies [23, 36, 41].”
BackgroundGwizdka, J., & Spence, I. (2006) · Proceedings of the American Society for Information Science and Technology · doi:10.1002/meet.14504301167 · Cited by 125 · cited 2×
“Papers exploring task difficulty have claimed a positive correlation between task difficulty and interaction [19, 26, 29].”
BackgroundJiang, J., He, D., & Allan, J. (2014) · Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval · doi:10.1145/2600428.2609633 · Cited by 125 · cited 1×
“[22] studied four types of tasks that were created using Li and Belkin’s [27] classification: known item, known subject, interpretive and exploratory.”
MethodFind it if you can: a game for modeling different types of web search success using interaction data
Ageev, M., Guo, Q., Lagun, D., & Agichtein, E. (2011) · Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval · doi:10.1145/2009916.2009965 · Cited by 116 · cited 1×
“could not be solved, or solved easily [1, 6].”
BackgroundMoffat, A., Thomas, P., & Scholer, F. (2013) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2505515.2507665 · Cited by 115 · cited 1×
“Other researchers have also started to use these tasks [7, 32], which demonstrate their potential usefulness for enabling research.”
BackgroundOn the history of evaluation in IR
Robertson, S. (2008) · Journal of Information Science · doi:10.1177/0165551507086989 · Cited by 107 · cited 1×
“TREC has a notion of a topic, which assumes most requests are topical or subject-based [33] and task is used to describe the specific TREC Track focus (e.”
Characterizing and predicting search engine switching behavior
White, R. W., & Dumais, S. (2009) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/1645953.1645967 · Cited by 97 · cited 1×
“Other studies have proposed that increases in search behavior are related to dissatisfaction and subsequently search engine switching [39] and seeking help from online QA forums [31].”
BackgroundWu, W.-C., Kelly, D., Edwards, A., & Arguello, J. (2012) · Proceedings of the 4th Information Interaction in Context Symposium · doi:10.1145/2362724.2362768 · Cited by 96
Self-citationStruggling or exploring?: disambiguating long search sessions
Hassan, A., White, R. W., Dumais, S. T., & Wang, Y.-M. (2014) · Proceedings of the 7th ACM international conference on Web search and data mining · doi:10.1145/2556195.2556221 · Cited by 91 · cited 1×
“Our results show the relative nature of interaction signals: in some situations a lot of interaction might indicate problems, while in other cases it represents satisfactory progress or positive experiences, which supports recent work on disambiguating interaction data [20].”
ResultWildemuth, B., Freund, L., & G. Toms, E. (2014) · Journal of Documentation · doi:10.1108/jd-03-2014-0056 · Cited by 85 · cited 6×
“[42] found fewer studies treated search task complexity as a subjective construct, but there is some evidence”
BackgroundInfluentialUser Variability and IR System Evaluation
Bailey, P., Moffat, A., Scholer, F., & Thomas, P. (2015) · Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/2766462.2767728 · Cited by 73
Evaluation Challenges and Directions for Information-Seeking Support Systems
Kelly, D., Dumais, S., & Pedersen, J. (2009) · Computer · doi:10.1109/mc.2009.82 · Cited by 72 · cited 1×
“Similar recommendations regarding sharable materials for IIR studies were made at an earlier NII Shonan Meeting [9], which focused on whole-session evaluation, as well as an earlier workshop on information-seeking support systems [25].”
BackgroundSelf-citationPredicting Search Task Difficulty
Arguello, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-06028-6_8 · Cited by 71 · cited 1×
“Since conducting the research reported in this paper, we have used these tasks in other research projects [4, 11, 16]; several of these studies used a crowdsourcing platform and one was done at a public library with members of our local community.”
MethodSelf-citationTask complexity, vertical display and user interaction in aggregated search
Arguello, J., Wu, W.-C., Kelly, D., & Edwards, A. (2012) · Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/2348283.2348343 · Cited by 68
Self-citationLeaving so soon?: understanding and predicting web search abandonment rationales
Diriye, A., White, R., Buscher, G., & Dumais, S. (2012) · Proceedings of the 21st ACM international conference on Information and knowledge management · doi:10.1145/2396761.2398399 · Cited by 67 · cited 1×
“Query abandonment, or queries without clicks, has also been used as a sign of dissatisfaction, or failure [17].”
Task Effects on Interactive Search: The Query Factor
Toms, E. G., O'Brien, H. L., Mackenzie, T., Jordan, C. A., Freund, L., Toze, S. L., Dawe, E., & MacNutt, A. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85902-4_31 · Cited by 66 · cited 1×
“Behavioral and self-report data were collected to understand and characterize differences among tasks, including with respect to difficulty, engagement and satisfaction.”
BackgroundTask difficulty as a predictor and indicator of web searching interaction
Kim, J. (2006) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/1125451.1125636 · Cited by 63 · cited 1×
“Papers exploring task difficulty have claimed a positive correlation between task difficulty and interaction [19, 26, 29].”
BackgroundWhen web search fails, searchers become askers: understanding the transition
Liu, Q., Agichtein, E., Dror, G., Maarek, Y., & Szpektor, I. (2012) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2348283.2348390 · Cited by 61 · cited 1×
“Other studies have proposed that increases in search behavior are related to dissatisfaction and subsequently search engine switching [39] and seeking help from online QA forums [31].”
BackgroundThe effect of cognitive abilities on information search for tasks of varying levels of complexity
Brennan, K., Kelly, D., & Arguello, J. (2014) · Proceedings of the 5th Information Interaction in Context Symposium · doi:10.1145/2637002.2637022 · Cited by 57 · cited 1×
“Since conducting the research reported in this paper, we have used these tasks in other research projects [4, 11, 16]; several of these studies used a crowdsourcing platform and one was done at a public library with members of our local community.”
MethodSelf-citationExploring and predicting search task difficulty
Liu, J., Liu, C., Cole, M., Belkin, N. J., & Zhang, X. (2012) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2396761.2398434 · Cited by 49 · cited 3×
“Papers exploring task difficulty have claimed a positive correlation between task difficulty and interaction [19, 26, 29].”
BackgroundTask-based information searching and retrieval
Toms, E. G. (2018) · Facet eBooks · doi:10.29085/9781856049740.005 · Cited by 42 · cited 5×
“Toms [36] observes that tasks have been used in two major ways in IR research: (1) as a vehicle for research (citing, for example TREC topics) and (2) as an object of study, where the researcher is interested in how different task types or properties impact search experiences.”
BackgroundMethodInfluentialTime pressure, user satisfaction and task difficulty
Crescenzi, A., Capra, R., & Arguello, J. (2013) · Proceedings of the American Society for Information Science and Technology · doi:10.1002/meet.14505001121 · Cited by 40 · cited 1×
“Since conducting the research reported in this paper, we have used these tasks in other research projects [4, 11, 16]; several of these studies used a crowdsourcing platform and one was done at a public library with members of our local community.”
MethodSelf-citationNSF workshop on task-based information search systems
Kelly, D., Arguello, J., & Capra, R. (2013) · ACM SIGIR Forum · doi:10.1145/2568388.2568407 · Cited by 37 · cited 1×
“At a recent workshop focused on task-based information search systems, the development of simulated search tasks that could be shared among research groups was identified as a major direction [24].”
BackgroundSelf-citationBig Macs and Eigenfactor scores: Don't let correlation coefficients fool you
Eschenfelder, K. R. (2010) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.v61:9 · Cited by 27
Singer, G., Norbisrath, U., & Lewandowski, D. (2012) · Information Interaction in Context Symposium (IIiX) · doi:10.1145/2362724.2362746 · Cited by 22 · cited 1×
“In general, studies have found that people engage in more search interactions when completing more complex tasks [28, 34].”
BackgroundWhole-Session Evaluation of Interactive Information Retrieval Systems (NII Shonan Meeting 2012-7).
Belkin, N. J., Dumais, S., Kando, N., & Sanderson, M. (2012) · NII Shonan Meet. Rep. · Cited by 14
Why do users feel search task difficult?
Liu, J., Kim, C. S., & Creel, C. (2013) · Proceedings of the American Society for Information Science and Technology · doi:10.1002/meet.14505001125 · Cited by 9 · cited 1×
“ACM 978-1-4503-3833-2/15/09…$15.00 DOI: http://dx.doi.org/10.1145/2808194.2809465”
InfluentialSearcher adaptation: A response to topic difficulty
Smith, C. L. (2008) · Proceedings of the American Society for Information Science and Technology · doi:10.1002/meet.2008.1450450381 · Cited by 7
Research works printed but not linked: 4
- 10.1002/asi.v56:10 · doi:10.1002/asi.v56:10
- 10.5555/2655780.2655902 · doi:10.5555/2655780.2655902
- Dumais , S. T. , & Belkin , N. J. ( 2005 ). The TREC Interactive Tracks: Putting the user into search . In E. M. Voorhees & D . K. Harman (Eds.) TREC: Experiment and Evaluation in Information Retrieval ( pp. 123 -- 153 ), Cambridge, MA : MIT Press . Dumais, S. T., & Belkin, N. J. (2005). The TREC Interactive Tracks: Putting the user into search. In E. M. Voorhees & D. K. Harman (Eds.) TREC: Experiment and Evaluation in Information Retrieval (pp. 123--153), Cambridge, MA: MIT Press.
- 10.5555/2655780.2655906 · doi:10.5555/2655780.2655906
Cited by
Towards searching as a learning process: A review of current perspectives and future directions
Rieh, S. Y., Collins-Thompson, K., Hansen, P., & Lee, H.-J. (2016) · Journal of Information Science · doi:10.1177/0165551515615841 · Cited by 208
“[26] also used Anderson and Krathwhol’s [9] taxonomy when they evaluated a set of search tasks in terms of levels of cognitive complexity across multiple domains.”
MethodCognitive Biases in Search: A Review and Reflection of Cognitive Biases in Information Retrieval
Azzopardi, L. (2021) · Proceedings of the 2021 Conference on Human Information Interaction and Retrieval · doi:10.1145/3406522.3446023 · Cited by 176
“number of items, this may not necessarily be the case, and it may even increase the cost of browsing [6, 38].”
BackgroundIncorporating User Expectations and Behavior into the Measurement of Search Effectiveness
Moffat, A., Bailey, P., Scholer, F., & Thomas, P. (2017) · ACM Transactions on Information Systems · doi:10.1145/3052768 · Cited by 107
“” We also use a third level, Analyze; tasks at this level of the hierarchy involve “breaking material into constituent parts, determining how the parts relate to one another and to an overall structure or purpose through differentiating, organizing, and attributing” [Kelly et al. 2015].”
MethodPredicting User Satisfaction with Intelligent Assistants
Kiseleva, J., Williams, K., Hassan Awadallah, A., Crook, A. C., Zitouni, I., & Anastasakos, T. (2016) · Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval · doi:10.1145/2911451.2911521 · Cited by 108
“Moreover, Kelly et al. [29] have provided evidence that the most complex search tasks were similar to the work [6] characterization of complex tasks with respect to having multiple interdependent parts that needed to be addressed separately.”
BackgroundSearching as Learning: Exploring Search Behavior and Learning Outcomes in Learning-related Tasks
Ghosh, S., Rath, M., & Shah, C. S. (2018) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3176349.3176386 · Cited by 102
“Several studies in LIS literature that have employed the taxonomy of learning to evaluate and classify various search tasks and that required different cognitive processes and demands from users, [9, 13, 14, 28, 32].”
BackgroundResult
Metadata
- Authors
- Kelly, D., Arguello, J., Edwards, A., & Wu, W.-C.
- Affiliations
- University of North Carolina at Chapel Hill (US)
- ORCID
- Arguello, Jaime
- Venue
- Proceedings of the 2015 International Conference on The Theory of Information Retrieval
- Publisher
- ACM
- Published
- 2015-09-27
- Pages
- 101-110
- OpenAlex
- W2069049590
- Cited by
- 155
- References
- 51
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 14 · 2023: 8 · 2022: 16 · 2021: 17 · 2020: 19 · 2019: 27 · 2018: 12 · 2017: 19 · 2016: 8 · 2015: 1
- FWCI
- 11.59
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- interactive information retrieval, task difficulty, user experience, search behavior, task evaluation, user satisfaction
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.