Web Mail is not Dead!: It's Just Not Human Anymore.

Many have noticed that personal communications have slowly moved from mail to social media and instant messaging platforms, especially with younger generation [6]. Yet Web Mail traffic continues to steadily grow. A paradox? Not really. We have observed at Yahoo Research that the nature of email traffic has significantly changed in the last two decades, and it is now dominated by machine-generated messages. These messages include hotel newsletters, from which users forgot to unsubscribe, repeated, and often annoying, notifications from a social media site, or critical information such as a flight e-ticket, a purchase invoice, or a telephone bill. In this talk, I first share some elements of this journey that led us to this critical finding that 90% of today's Web Mail is sent by automatic scripts [1]. I then discuss the challenges and opportunities this drastic change offers. First the key challenge: namely, the need for Web mail services to revisit their usage assumptions and their traditional features in light of this change. An obvious example is the \"reply\" button being displayed by default below messages sent from a \"no-reply@\" sender. Another feature is mail classification, which has finally experienced some changes in the last few years, [4]. I then discuss the opportunities in this era of big data. One first insight is that messages that have been generated by a same script, share some semantic commonality. Being able to automatically cluster such messages, and map such clusters into \"templates\" brings great value for discovering meaning, for generalizing findings and predicting behaviors [5]. A second insight is that within this commonality, the differences bring even more value, which allows highlighting what makes individuals unique within a crowd. In particular we discuss extraction techniques that automatically identify these unique elements [2]. Yet, they also present a clear risk in terms of privacy and I describe the absolute need for guaranteeing k-anonymity in our mining techniques, [3]. I conclude by encouraging the research community to explore this new domain of Web mail search and data mining.