Personalized document recommendation systems aim to provide users with a quick shortcut to the documents they may want to access next, usually with an explanation about why the document is recommended. Previous work explored various methods for better recommendations and better explanations in different domains. However, there are few efforts that closely study how users react to the recommended items in a document recommendation scenario. We conducted a large-scale log study of users’ interaction behavior with the explainable recommendation on one of the largest cloud document platforms office.com. Our analysis reveals a number of factors, including display position, file type, authorship, recency of last access, and most importantly, the recommendation explanations, that are associated with whether users will recognize or open the recommended documents. Moreover, we specifically focus on explanations and conduct an online experiment to investigate the influence of different explanations on user behavior. Our analysis indicates that the recommendations help users access their documents significantly faster, but sometimes users miss a recommendation and resort to other more complicated methods to open the documents. Our results suggest opportunities to improve explanations and more generally the design of systems that provide and explain recommendations for documents.

In many computing scenarios, an individual may choose to interact with a service in a variety of roles, and may therefore create a set of accounts respectively representing the service. However, the use of multiple accounts by the same individual may introduce considerable administrative complications (e.g., failing to update all accounts with new information results in stale and/or conflicting account information), and may reduce the efficiency and/or scalability of the service. Presented herein are techniques for enabling individuals to interact with services through various roles. Such techniques involve evaluating the individual's role determinants to identify and automatically select the individual's current role; selecting a current role profile, as a subset of the details of the individual profile that are associated with the current role, and excluding details that are not associated with the current role; and performing the service according to the current role profile of the individual.

Complex software applications expose hundreds of commands to users through intricate menu hierarchies. One of the most popular productivity software suites, Microsoft Office, has recently developed functionality that allows users to issue free-form text queries to a search system to quickly find commands they want to execute, retrieve help documentation or access web results in a unified interface. In this paper, we analyze millions of search sessions originating from within Microsoft Office applications, collected over one month of activity, in an effort to characterize search behavior in productivity software. Our research brings together previous efforts in analyzing command usage in large-scale applications and efforts in understanding search behavior in environments other than the web. Our findings show that users engage primarily in command search, and that re-accessing commands through search is a frequent behavior. Our work represents the first large-scale analysis of search over command spaces and is an important first step in understanding how search systems integrated with productivity software can be successfully developed.

In many computing scenarios, an individual may interact with a device in a variety of roles, such as a student, an intern, and a gamer. While the individual may utilize the device in different ways for each role (e.g., using a particular set of files, applications, websites, and services), the device is not typically informed of the individual's role, and provides generalized device behavior irrespective of the individual's role. Presented herein are techniques for adapting device behavior based on the current role of the individual. Such techniques involve evaluating the individual's role determinants to identify and automatically select the individual's current role; selecting a current role profile, as a subset of the details of the individual profile that are associated with the current role, and excluding details that are not associated with the current role; and adjusting the device behavior according to the current role profile of the individual.

One or more techniques and/or systems are provided for providing an answer scheme for an information request. For example a requester user may submit an information request seeking an informational answer (e.g., how far is the moon from the Earth; what are fun Cancun activities; is my drawing an accurate octagon; etc.). The information request may be evaluated to identify an information request property (e.g., an interesting property, a factual question property, an opinion property, an expertise level property, etc.). An answerer pool and/or an interaction type may be identified based upon the information request property (e.g., a chat group of scientists, a onetime text message answer from a paid expert, a vacation forum, a screen sharing session, etc.). An answer scheme, comprising the answerer pool and/or the interaction type, may be provided to the requester user for obtaining the informational answer.

In this paper, we propose a new framework for searchable web sites recommendation. Given a query, our system will recommend a list of searchable web sites ranked by relevance, which can be used to complement the web page results and ads from a search engine. We model the conditional probability of a searchable web site being relevant to a given query in term of three main components: the language model of the query, the language model of the content within the web site, and the reputation of the web site searching capability (static rank). The language models for queries and searchable sites are built using information mined from client-side browsing logs. The static rank for each searchable site leverages features extracted from these client-side logs such as number of queries that are submitted to this site, and features extracted from general search engines such as the number of web pages that indexed for this site, number of clicks per query, and the dwell-time that a user spends on the search result page and on the clicked result web pages. We also learn a weight for each kind of feature to optimize the ranking performance. In our experiment, we discover 10.5 thousand searchable sites and use 5 million unique queries, extracted from one week of log data to build and demonstrate the effectiveness of our searchable web site recommendation system.

PROBLEM TO BE SOLVED: To enable the generation of an input for more reliably classifying electronic messages, for example, as unwanted and/or unsolicited electronic messages, which are not requested by a receiver to be transmitted, by supplying the electronic messages to a message classifying module. SOLUTION: An answer document, in which an answer hash value calculated from the combination of an answer document and a puzzle input hash value becomes an answer value for a computational puzzle, and en electronic message including electronic message data are transmitted to a receiving computer system. COPYRIGHT: (C)2010,JPO&INPIT