PMA A Mobile ContextAware Personal Messaging Assistant Senaka
PMA: A Mobile Context-Aware Personal Messaging Assistant Senaka Buthpitiya Deepthi Madamanchi Sumalatha Kommaraju Martin Griss Cy. Lab Mobility Research Center Carnegie Mellon Silicon Valley C a r n e g i e M e l l 1
Agenda • Introduction to Email Sorting • Related Work • PMA – Design and Architecture • Experiments & Results • Conclusion • Future Work C a r n e g i e M e l l 2
What is a “Mobile Context-Aware Personal Messaging Assistant”? • An advanced rule-based email management system which uses the mobile user’s context and email content to • classify emails • prioritize emails • selectively deliver key messages to mobile phone • Uses real-time context information from: • hard sensors (GPS, accelerometer, etc. ) on Mobile phone • soft sensors (calendar, …) C a r n e g i e M e l l 3
Email Flooding in the Real World Busy professionals receive in excess of 50 emails per day, 23% require immediate attention 13% require attention later 64% are unimportant Problem is even worse for mobile professionals Difficult to sort through emails on mobile devices Wastes precious bandwidth and battery life End Result: C a r n e g i e M e l l Wastes time sorting through unwanted emails Drastic reduction in productivity! 4
Problems • Most email sorting/classification programs take only email-content into account • Depending on users’ contexts, the emails that they wish to see vary • Depending on the users’ contexts the number of emails they can scan through varies • Email sorting/classification programs consider importance only Importance and urgency are orthogonal yet affects email sorting equally C a r n e g i e M e l l Unimportant Important Non. Urgent Evite for a BBQ. From manager: Client visit pushed back by another month. Urgent Online auction: you were out bid. Son missed his bus, pick him up from school. 5
PMA Architecture PMA separately rates emails according importance and urgency using context information and email content e. g. – email from the user’s boss about present meeting is important and very urgent PMA decides on what-to deliver, how-to-deliver and where-to-deliver according to user’s context e. g. – deliver as SMS, text-to-voice SMS, forward to co-worker C a r n e g i e M e l l Uses a rule-based system for decision making 7
Context Information Gathered from hard sensors on a Nokia N 95 (which also doubles as a delivery point for selected emails) Gathered from soft sensors such as Google Calendar Context includes all information related to user including, • Static context such as name and family details • Dynamic context such as meeting topic, driving speed • User preferences C a r n e g i e M e l l 8
Experiment - 1 AIM – Test effectiveness of PMA’s urgency and importance classifiers For various user contexts, • PMA classifies a test set of emails separately for importance and urgency • compared against ratings for the same emails by user Number of type X emails correctly classified by PMA Recall = Total number of emails selected by users as type X Number of type X emails correctly classified by PMA Precision = C a r n e g i e M e l l Number of emails classified by PMA as X 9
Results Summary of precision and recall of importance classification Random PMA Recall 33. 3% 96. 3% Precision 26. 1% 88. 2% Summary of precision and recall of urgency classification C a r n e g i e M e l l Random PMA Recall 8. 3% 94. 8% Precision 8. 3% 92. 6% 10
Experiment - 2 AIM – Test effectiveness of PMA’s delivery agent and overall system For various user contexts, • PMA decides on what action to perform with a given email • SMS to user • Send to users as text-to-voice SMS • Folder for later viewing • Take no action • compared against user’s expected action on each email C a r n e g i e M e l l 11
Results C a r n e g i e M e l l 12
Conclusions PMA sorts and delivers messages that are relevant to the user in his current context, effectively • Uses emails content and user’s context information for decision making PMA uses separate scales to measure urgency and importance of an email PMA is scalable for all inbox sizes C a r n e g i e M e l l PMA is easily personalized to suit the requirements of any user for better accuracy 13
Future Work Performance of PMA • Machine learning schemes to automate the learning from user feedback • Improve run-time Generalization of PMA • Support for various email accounts Yahoo! mail, Hotmail, etc. • Support for additional message types (SMS, IM, RSS, etc. ) Personalization of PMA C a r n e g i e M e l l • User interface to create/edit custom rules • Mobile device interface for feedback and usability 14
Thank You C a r n e g i e M e l l
- Slides: 14