Bahareh Sarrafzadeh

Bahareh Sarrafzadeh

Auto-generated profile, based on publicly available information

Bahareh Sarrafzadeh

Microsoft, Redmond, Washington, USA

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 September 2024 in ACM Transactions on Interactive Intelligent Systems
Verified
Journal Article
Open access
CLConnor Lawless
Connor Lawless
JSJakob Schoeffer
Jakob Schoeffer
LLLindy Le
Lindy Le
KRKael Rowan
Kael Rowan
SSShilad Sen
Shilad Sen
BSBahareh Sarrafzadeh
Bahareh Sarrafzadeh
A critical factor in the success of many decision support systems is the accurate modeling of user preferences. Psychology research has demonstrated that users often develop their preferences during the elicitation process, highlighting the pivotal role of system-user interaction in developing personalized systems. This paper introduces a novel approach, combining Large Language Models (LLMs) with Constraint Programming to facilitate interactive decision support. We study this hybrid framework through the lens of meeting scheduling, a time-consuming daily activity faced by a multitude of information workers. We conduct three studies to evaluate the novel framework, including a diary study to characterize contextual scheduling preferences, a quantitative evaluation of the system’s performance, and a user study to elicit insights with a technology probe that encapsulates our framework. Our work highlights the potential for a hybrid LLM and optimization approach for iterative preference elicitation, and suggests design considerations for building systems that support human-system collaborative decision-making processes.

26 August 2014
Verified
Conference Paper
Open access
PDF file
BSBahareh Sarrafzadeh
Bahareh Sarrafzadeh
OVOlga Vechtomova
Olga Vechtomova
VJVlado Jokic
Vlado Jokic

19 April 2023
Verified
Conference Paper
Open access
LMLillio Mok
Lillio Mok
LSLu Sun
Lu Sun
SSShilad Sen
Shilad Sen
BSBahareh Sarrafzadeh
Bahareh Sarrafzadeh
Organizations are becoming increasingly distributed and many need to collaborate synchronously over great geographical distances. Despite a rich body of literature on spatially-distanced meetings, gaps remain in our understanding of temporally-distanced meetings. Here, we characterize cross time zone collaborations by analyzing 20 million meetings scheduled at a multinational corporation, Microsoft, supported by a survey on how 130 employees perceive their scheduling needs. We find that cross time zone meetings are closely associated with scheduling patterns around early morning and late evening hours, which are challenging and discordant with employees’ stated temporal preferences. Additionally, the burdens of meeting across time boundaries are asymmetrically distributed among workers at different levels of the organization and different geolocations. Nonetheless, we further observe evidence that cross time zone attendees are organizationally distant and diverse, suggesting that addressing these challenges by limiting meetings would disafford employees the opportunities to connect. We conclude by sharing opportunities for facilitating cross time zone meetings that foster healthier global collaborations.

7 November 2024 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
LSLu Sun
Lu Sun
LMLillio Mok
Lillio Mok
SSShilad Sen
Shilad Sen
BSBahareh Sarrafzadeh
Bahareh Sarrafzadeh
As processes around hybrid work, spatially distant collaborations, and work-life boundaries grow increasingly complex, managing workers' schedules for synchronous meetings has become a critical aspect of building successful global teams. However, gaps remain in our understanding of workers' scheduling preferences and practices, which we aim to fill in this large-scale, mixed-methods study of individuals' calendars in a multinational organization. Using interviews with eight participants, survey data from 165 respondents, and telemetry data from millions of meetings scheduled by 211 thousand workers, we characterize scheduling preferences, practices, and their relationship with each other and organizational factors. We find that temporal preferences can be broadly classified as either cyclical, such as suitability of certain days, or relational, such as dispersed meetings, at various time scales. Furthermore, our results suggest that these preferences are disconnected from actual practice--albeit with several notable exceptions--and that individual differences are associated with factors like meeting load, time-zones, importance of meetings to job function, and job titles. We discuss key themes for our findings, along with the implications for calendar and scheduling systems and socio-technical systems more broadly.