TY - GEN
T1 - Unsubscription
T2 - 11th ACM International Conference on Web Search and Data Mining, WSDM 2018
AU - Gamzu, Iftah
AU - Lewin-Eytan, Liane
AU - Silberstein, Natalia
N1 - Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/2/2
Y1 - 2018/2/2
N2 - The constant growth of machine-generated mail, which today consists of more than 90% of non-spam mail traffic, is a major contributor to information overload in email, where users become overwhelmed with a flood of messages from commercial entities. A large part of this traffic is often junk mail that the user would prefer not to receive. Surprisingly, nearly 95% of this traffic is in fact solicited by the users themselves in the form of subscriptions to mailing services. These subscriptions are many times unintentional. Although unsubscription option from such services is enforced by commercial laws, it is hardly actually used by users. We perform a large scale study of unsubscribable traffic, namely, messages that provide unsubscription option to users. We consider users behavior over such traffic in Yahoo Web mail service, and demonstrate a significant gap between users low interest in this traffic, and their lack of active behavior in decreasing its load. We conjecture that the cause of this gap is the lack of an efficient and easily accessible mechanism that would help users to unsubscribe. We validate our conjecture with an online large scale experiment, where we provide users with a novel mail feature for managing unsubscribable traffic, based on personalized recommendations. The experiment demonstrates the imminent need that exists for such a mechanism.
AB - The constant growth of machine-generated mail, which today consists of more than 90% of non-spam mail traffic, is a major contributor to information overload in email, where users become overwhelmed with a flood of messages from commercial entities. A large part of this traffic is often junk mail that the user would prefer not to receive. Surprisingly, nearly 95% of this traffic is in fact solicited by the users themselves in the form of subscriptions to mailing services. These subscriptions are many times unintentional. Although unsubscription option from such services is enforced by commercial laws, it is hardly actually used by users. We perform a large scale study of unsubscribable traffic, namely, messages that provide unsubscription option to users. We consider users behavior over such traffic in Yahoo Web mail service, and demonstrate a significant gap between users low interest in this traffic, and their lack of active behavior in decreasing its load. We conjecture that the cause of this gap is the lack of an efficient and easily accessible mechanism that would help users to unsubscribe. We validate our conjecture with an online large scale experiment, where we provide users with a novel mail feature for managing unsubscribable traffic, based on personalized recommendations. The experiment demonstrates the imminent need that exists for such a mechanism.
KW - Machine-generated mail
KW - Mail mining
KW - Unsubscription recommendations
UR - http://www.scopus.com/inward/record.url?scp=85046896128&partnerID=8YFLogxK
U2 - 10.1145/3159652.3159698
DO - 10.1145/3159652.3159698
M3 - Conference contribution
AN - SCOPUS:85046896128
T3 - WSDM 2018 - Proceedings of the 11th ACM International Conference on Web Search and Data Mining
SP - 189
EP - 197
BT - WSDM 2018 - Proceedings of the 11th ACM International Conference on Web Search and Data Mining
PB - Association for Computing Machinery, Inc
Y2 - 5 February 2018 through 9 February 2018
ER -