Measuring improvement in user search performance resulting from optimal search tips

Moraveji, Neema; Russell, Daniel M.; Bien, Jacob; Mease, David

doi:10.1145/2009916.2009966

Cited by 32 publications

(30 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both approaches have been applied to search and recommenders. Educational approaches, such as in [3] or [25] can be considered to be examples of boosting, whereas query suggestions and manipulating the search box size [4] are nudges. What is lacking in the literature, however, is an understanding of how boosts and nudges can be applied to food choices from search and recommender systems and whether such approaches can lead to any real behavioural change.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Food Choice Biases for Healthier Recipe Recommendation

Elsweiler

Trattner

Harvey

2017

Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

139

View full text Add to dashboard Cite

By incorporating healthiness into the food recommendation / ranking process we have the potential to improve the eating habits of a growing number of people who use the Internet as a source of food inspiration. In this paper, using insights gained from various data sources, we explore the feasibility of substituting meals that would typically be recommended to users with similar, healthier dishes. First, by analysing a recipe collection sourced from Allrecipes.com, we quantify the potential for nding replacement recipes, which are comparable but have di erent nutritional characteristics and are nevertheless highly rated by users. Building on this, we present two controlled user studies (n=107, n=111) investigating how people perceive and select recipes. We show participants are unable to reliably identify which recipe contains most fat due to their answers being biased by lack of information, misleading cues and limited nutritional knowledge on their part. By applying machine learning techniques to predict the preferred recipes, good performance can be achieved using low-level image features and recipe meta-data as predictors. Despite not being able to consciously determine which of two recipes contains most fat, on average, participants select the recipe with the most fat as their preference. The importance of image features reveals that recipe choices are often visually driven. A nal user study (n=138) investigates to what extent the predictive models can be used to select recipe replacements such that users can be "nudged" towards choosing healthier recipes. Our ndings have important implications for online food systems. KEYWORDSFood RecSys; human decision making; behavioural change; information behaviour ACM Reference format:

show abstract

Section: Related Workmentioning

confidence: 99%

Exploiting Food Choice Biases for Healthier Recipe Recommendation

Elsweiler

Trattner

Harvey

2017

Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

139

View full text Add to dashboard Cite

show abstract

“…These findings are not conceptualized as learning although they include learning processes remembering and understanding. However, in an exceptional study, Moraveji and his colleagues [15] analysed how tactical search feature tips were associated with search performance. These tips expanded user awareness of the task-relevant tools and features of the search application.…”

Section: From Searching To Learningmentioning

confidence: 99%

Searching as learning: A systematization based on literature

Vakkari

2016

Journal of Information Science

135

101

View full text Add to dashboard Cite

The paper surveys empirical studies on the relations between information searching and learning, and presents some reflections about learning in a search process based on the findings. First, the meaning of the concepts 'learning' and 'searching' is briefly defined. Learning is conceptualized as changes in one's knowledge structures. Then it is described more in detail how learning occurs in the search process. The point of departure is to focus on tasks that require the restructuring of knowledge structures and to analyse how gradual stabilization of those structures is related to accessing and interacting with information sources. After that, empirical studies on searching and learning are categorized by identifying independent and dependent variables in those studies. In conclusion, some general remarks on the topic are presented.

show abstract

“…These hints can be learned from more successful and advanced users [2,226] or provide examples that may work generically for some search intents, such as leading searchers to longer queries [1]. Moraveji et al [153] showed that the presentation of optimal search tips, for tasks where they are known to have benefit, can have a lasting impact on searcher efficiency. Savenkov and Agichtein [191] showed that providing a searcher with task-specific hints improves both success and satisfaction.…”

Section: Frustration and Difficultymentioning

confidence: 99%

“…Savenkov and Agichtein [191] showed that providing a searcher with task-specific hints improves both success and satisfaction. Conversely, generic hints decrease both success and satisfaction [153,191], indicating that it is paramount to understand what a searcher is struggling with before providing hints.…”

Section: Frustration and Difficultymentioning

confidence: 99%

“…Learning the relationship between task success and the nature of the anticipated query reformulation allows search systems to generate human-readable hints about which types of reformulations to leverage (e.g., "add an action" leads to the highest proportion of pivotal queries, per Figure 5.14), and propose them in real time as people are searching. Moraveji et al [153] showed that the presentation of optimal search hints, where they are presented for a task where they are known to have benefit, can have a lasting impact on searcher efficiency. Future research could investigate whether hints derived from the reformulation strategies are optimal and whether they have a lasting impact on searcher efficiency.…”

Section: Theme 2-struggling and Success In Web Searchmentioning

confidence: 99%

See 1 more Smart Citation

Context & Semantics in News & Web Search

Odijk

2016

SIGIR Forum

View full text Add to dashboard Cite

This thesis presents research towards a core aim of information retrieval (IR): providing users with easy access to information. Three research themes guide the research presented in this thesis, contributing to three aspects of IR research: the domain in which an IR system is used, the users interacting with the system, and the different access scenarios in which these users engage with an IR system. Central to these research themes is the aim to gain insights into the behavior of searchers and develop algorithms to support them in their quest, whether it is a researcher exploring or studying a large collection, a web searcher struggling to find something, or a television viewer searching for related content. The first research theme is motivated by the information seeking tasks of researchers exploring and studying large collections. To enable their search on a larger scale, we propose computational methods to connect collections and to infer the perspective offered in a news story. Motivated by how historians select documents for close reading, we propose novel methods for connecting collections using automatically extracted temporal references. To illustrate how these algorithms can be used to automatically create connections between collections, we introduce a novel search interface to explore and analyze the connected collections. The interface highlights different perspectives and requires little domain knowledge. Based on how communication scientists study framing in news, we propose an automatic thematic content analysis approach. The second research theme is addressed in a mixed-methods study on how web searchers behave when they cannot find what they are looking for. Based on large-scale log analysis, crowd-sourced labeling, and predictive modeling we show behavioral differences given task success and failure. Based on these findings we propose ways in which systems can reduce struggling in search. To support searchers, we propose and evaluate algorithms that accurately predict the nature of future actions and their anticipated impact on search outcomes. Our findings have implications for the design of search systems that help searchers struggle less and succeed more. In the third and final research theme, we consider a pro-active search scenario, specifically in a live television setting. We propose algorithms that leverage contextual information to retrieve diverse related content for a leaned-back TV viewer. While watching television, people increasingly consume additional content related to what they are watching. Two methods to automatically retrieve content based on subtitles are introduced, one using entity linking, and one that uses reinforcement learning to generate effective queries for finding related content. Both methods are highly efficient and are currently used in a live television setting in near real time. Each research chapter in this thesis provides insights and algorithms that help searchers when using IR applications. For varying domains, users, and access scenarios, the research presented in this thesis improves the ease of access to information.

show abstract

Measuring improvement in user search performance resulting from optimal search tips

Cited by 32 publications

References 25 publications

Exploiting Food Choice Biases for Healthier Recipe Recommendation

Exploiting Food Choice Biases for Healthier Recipe Recommendation

Searching as learning: A systematization based on literature

Context & Semantics in News & Web Search

Contact Info

Product

Resources

About