A typical person has numerous online friends that, according to studies, the person often consults for opinions and advice. However, public broadcasting a question to all friends risks social capital when repeated too often, is not tolerant to topic sensitivity, and can result in no response, as the message is lost in a myriad of status updates. Direct messaging is more personal and avoids these pitfalls, but requires manual selection of friends to contact, which can be time consuming and challenging. A user may have difficulty guessing which of their numerous online friends can provide a high quality and timely response. We demonstrate a working system that addresses these issues by returning an ordered subset of friends predicting (a) near-term availability, (b) willingness to respond and (c) topical knowledge, given a query. The combination of these three aspects are unique to our solution, and all are critical to the problem of obtaining timely and relevant responses. Our system acts as a decision aid - we give insight into why each friend was recommended and let the user decide whom to contact.

We present the design of Symphony, a platform that enables non-developers to build and deploy a new class of search-driven applications that combine their data and domain expertise with content from search engines and other web services. The Symphony prototype has been built on top of Microsoft's Bing infrastructure. While Symphony naturally makes use of the customization capabilities exposed by Bing, its distinguishing feature is the capability it provides to the application creator to combine their proprietary data and domain expertise with content obtained from Bing. They can also integrate specialized data obtained from web services to enhance the richness of their applications. Finally, Symphony is targeted at non-developers and provides cloud services for the creation and deployment of applications.

Classification is a core task in knowledge discovery and data mining, and there has been substantial research effort in developing sophisticated classification models. In a parallel thread, recent work from the NLP community suggests that for tasks such as natural language disambiguation even a simple algorithm can outperform a sophisticated one, if it is provided with large quantities of high quality training data. In those applications, training data occurs naturally in text corpora, and high quality training data sets running into billions of words have been reportedly used.

In web search today, a user types a few keywords which are then matched against a large collection of unstructured web pages. This leaves a lot to be desired for when the best answer to a query is contained in structured data stores and/or when the user includes some structural semantics in the query.

We consider the problem of mining association rules on a shared nothing multiprocessor. We present three algorithms that explore a spectrum of trade-offs between computation, communication, memory usage, synchronization, and the use of problem specific information. The best algorithm exhibits near perfect scaleup behavior, yet requires only minimal overhead compared to the current best serial algorithm.