Stephen Dill

SemTag and seeker: bootstrapping the semantic web via automated semantic annotation

This paper describes Seeker, a platform for large-scale text analytics, and SemTag, an application written on the platform to perform automated semantic tagging of large corpora. We apply SemTag to a collection of approximately 264 million web pages, and generate approximately 434 million automatically disambiguated semantic tags, published to the web as a label bureau providing metadata regarding the 434 million annotations. To our knowledge, this is the largest scale semantic tagging effort to date.We describe the Seeker platform, discuss the architecture of the SemTag application, describe a new disambiguation algorithm specialized to support ontological disambiguation of large-scale data, evaluate the algorithm, and present our final results with information about acquiring and making use of the semantic tags. We argue that automated large scale semantic tagging of ambiguous content can bootstrap and accelerate the creation of the semantic web.

A case for automated large-scale semantic annotation

Abstract This paper describes Seeker, a platform for large-scale text analytics, and SemTag, an application written on the platform to perform automated semantic tagging of large corpora. We apply SemTag to a collection of approximately 264 million web pages, and generate approximately 434 million automatically disambiguated semantic tags, published to the web as a label bureau providing metadata regarding the 434 million annotations. To our knowledge, this is the largest scale semantic tagging effort to date. We describe the Seeker platform, discuss the architecture of the SemTag application, describe a new disambiguation algorithm specialized to support ontological disambiguation of large-scale data, evaluate the algorithm, and present our final results with information about acquiring and making use of the semantic tags. We argue that automated large-scale semantic tagging of ambiguous content can bootstrap and accelerate the creation of the semantic web.

A CRM system for social media: challenges and experiences

The social Customer Relationship Management (CRM) landscape is attracting significant attention from customers and enterprises alike as a sustainable channel for tracking, managing and improving customer relations. Enterprises are taking a hard look at this open, unmediated platform because the community effect generated on this channel can have a telling effect on their brand image, potential market opportunity and customer loyalty. In this work we present our experiences in building a system that mines conversations on social platforms to identify and prioritize those posts and messages that are relevant to enterprises. The system presented in this work aims to empower an agent or a representative in an enterprise to monitor, track and respond to customer communication while also encouraging community participation.

Global differences in attributes of email usage

Email usage data from users in a large enterprise were analyzed according to country and geographical regions to explore for differences. Data of 13,877 employees from 29 countries in a global technology company were analyzed. We found statistically significant differences in several attributes of email usage. Users in the U.S. tend to retain larger numbers of email messages while Latin American countries keep fewer messages. European countries tend to file more of their email into folders and Asian countries tend to do less so. These differences in filing behavior are not correlated with Hofstedes Uncertainty Avoidance Index. This research adds another dimension for studies of email usage which previously have not reported the geographical source of their data.

Team analytics: understanding teams in the global workplace

Many medium and large companies maintain internal employee directories. Unfortunately, most directories only allow the lookup of individual profiles, one profile at a time. Team Analytics is a novel application that integrates information from disparate enterprise tools for groups of people. Besides accelerating the lookup process, Team Analytics also displays information that is only available in the group context, such as an organizational chart and time zone awareness. We present the Team Analytics application, its integration with our corporate email client, and results from a user survey that evaluates various aspects of the application.

Ownership and Evolution of Local Process Representations

Knowledge workers tailor collaborative business processes to local conditions. They own (i.e., create and maintain) representations of these local processes (such as checklists) to guide the work. Our goal is to design tools to support the ownership of collaborative local processes by enabling workers to flexibly adapt process representations to work situations. This paper focuses on how workers evolve representations for collaborative, locally-owned processes by updating them from situated experiences to keep up with changing business conditions. To understand this, we conducted a field study and a lab study. From the field study, we describe how factors like group roles and documentation purposes affect the evolution of process representations. Based on these observations, we propose a model of the practice of evolving local process representations that provides a framework for understanding activity documentation needs. The lab study then provides behavioral details on the ways people carried out the evolution practice. These studies yield design implications for collaborative activity support tools.