Email has scaled our ability to communicate with large groups, but has not equivalently scaled our ability to listen and respond. For example, emailing many people for feedback requires either impersonal surveys or manual effort to hold many similar conversations. To scale personalized conversations, we introduce techniques that exploit similarities across conversations to recycle relevant parts of previous conversations. These techniques reduce the authoring burden, save senders' time, and maintain recipient engagement through personalized responses. We introduce MyriadHub, a mail client where users start conversations and then crowd workers extract underlying conversational patterns and rules to accelerate responses to future similar emails. In a within-subjects experiment comparing MyriadHub to existing mass email techniques, senders spent significantly less time planning events with MyriadHub. In a second experiment comparing MyriadHub to a standard email survey, MyriadHub doubled the recipients' response rate and tripled the number of words in their responses.

Social costs and limited reach inhibit our use of social capital to solicit help. However, individuals are not the only holders of social capital: groups also possess reputations and social capital, and are often prepared to vouch for their own members. In this paper, we design methods for mobilizing this collective social capital in sociotechnical systems, enabling an individual to ask a trusted group whether it is willing to invest its reputation in doing them a favor. We instantiate this concept with Founder Center, a web platform in which members of a local entrepreneurship accelerator ask the accelerator community to collectively make them introductions to potential funders. In a field experiment, enabling access to collective social capital in this community nearly doubled the odds of members making a social capital request. Requests fulfilled utilizing collective social capital were at least as effective as ones utilizing traditional interpersonal social capital.

This paper introduces privacy and accountability techniques for crowd-powered systems. We focus on email task management: tasks are an implicit part of every inbox, but the overwhelming volume of incoming email can bury important requests. We present EmailValet, an email client that recruits remote assistants from an expert crowdsourcing marketplace. By annotating each email with its implicit tasks, EmailValet's assistants create a task list that is automatically populated from emails in the user's inbox. The system is an example of a valet approach to crowdsourcing, which aims for parsimony and transparency in access con-trol for the crowd. To maintain privacy, users specify rules that define a sliding-window subset of their inbox that they are willing to share with assistants. To support accountability, EmailValet displays the actions that the assistant has taken on each email. In a weeklong field study, participants completed twice as many of their email-based tasks when they had access to crowdsourced assistants, and they became increasingly comfortable sharing their inbox with assistants over time.

People complete tasks more quickly when they have concrete plans. However, they often fail to create such action plans. (How) can systems provide these concrete steps automatically? This article demonstrates that these benefits can also be realized when these plans are created by others or reused from similar tasks. Four experiments test these approaches, finding that people indeed complete more tasks when they receive externally-created action plans. To automatically provide plans, we introduce the Genies workflow that combines benefits of crowd wisdom, collaborative refinement, and automation. We demonstrate and evaluate this approach through the TaskGenies system, and introduce an NLP similarity algorithm for reusing plans. We demonstrate that it is possible for people to create action plans for others, and we show that it can be cost effective.