From information needs to action needs: towards contextual app search and recommendation

Evgeniy Gabrilovich, Yahoo! Research


Classical IR is centered on the concept of an information need, which can be satisfied by (reading) one or more documents. Yet people rarely search merely to satisfy their curiosity; rather, they search the Web to get things done. Imagine a search engine that instead of offering a multitude of Web pages returns applications (apps) that directly help the users accomplish their goals. Inspired by the notion of an information need, we formulate the concept of an action need, which can be satisfied by a single app or a sequence thereof. Examples of action needs include reserving a restaurant table, booking a flight or an entire vacation, and comparison shopping. Although related to collaborative filtering, recommending apps in Web search is a more powerful paradigm as it considers not only users’ past activity and similarity to other users, but also their current context and action need. Contextual recommendation of applications is particularly useful in mobile Web search, where the limited form factor of the device leads the users to appreciate any assistance they can get.

One part of this vision, namely, developing a large ecosystem of apps to satisfy diverse user needs, is being already addressed on many platforms. Today, apps are ubiquitous in smart phones, and are becoming more common on desktop computers and even in browsers. This proliferation of apps is primarily due to the advent of online application stores, which revolutionized consumer software delivery. Whereas in the past, software was relatively expensive and primarily distributed through retail stores or manufacturers’ direct sales, modern app stores offer low transaction costs and integrated user experience, thus encouraging consumers to install new software at heretofore unseen prices, often under $1.

However, while there exist literally hundreds of thousands of apps, actually finding an app relevant to the user’s current action need is far from trivial. Apps are characterized by a plurality of features of different nature (including their textual descriptions, reviews, and ratings), and pose challenges reminiscent of those in retrieving other multimedia items. Designing app search systems therefore calls for principled IR techniques, such as query analysis and rewriting, sophisticated app indexing, learning to rank, and location awareness. App retrieval poses numerous research questions, including how to trigger apps for incoming search queries and how to speed-up user interaction with the apps by learning to pre-fill application input. Recommending relevant apps (both paid and free) in Web search also leads to interesting monetization opportunities. As opposed to sponsored search ads, however, pro bono apps can co-exist with paid ones, as long as they help the user satisfy his action needs (and thus help the search engine keep the user satisfied). Designing a monetization mechanism for apps needs to steer clear of the limitations of the current sponsored search systems, where short bid phrases often make it difficult to assess the relevance of ads. Finally, observing users’ interaction with apps enables better characterization of users’ interests.

This talk will introduce the emerging field of contextual app search and recommendation, and discuss its technical challenges and promising research directions.

This is joint work with Zhaohui Zheng, Yahoo! Labs China, Beijing.


Evgeniy Gabrilovich is a Senior Research Scientist and Manager of the NLP & IR Group at Yahoo! Research. His research interests include information retrieval, machine learning, and computational linguistics. Evgeniy is a recipient of the 2010 Karen Sparck Jones Award for his contributions to natural language processing and information retrieval. He served as a Senior PC member or Area Chair at SIGIR, AAAI, IJCAI, WWW, WSDM, EMNLP, ICDM, and ICWSM. He organized a number of workshops and taught multiple tutorials at SIGIR, ACL, IJCAI, AAAI, CIKM, and EC. Evgeniy earned his MSc and PhD degrees in Computer Science from the Technion - Israel Institute of Technology. In his Ph.D. thesis, he developed a methodology for using large scale repositories of world knowledge (e.g., all the knowledge available in Wikipedia) to enhance text representation beyond the bag of words.