<div dir="ltr"><br clear="all">Hello Everyone,<br>We are having our reading group<br><b> </b><span style="background-color:rgb(255,242,204)"><b><span style="background-color:rgb(255,217,102)">today at 2 pm in the Conference room in the MAT conference room </span></b><br>
</span>
<div>
<br></div><div>We will discuss:<br><a href="http://cs.stanford.edu/people/jure/pubs/beerrec-www13.pdf" target="_blank">From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews</a>
by J. McAuley, J. Leskovec.
<i>ACM International Conference on World Wide Web (WWW)</i>, 2013<br><br></div><div>Here is abstract:<br><br><i>Recommending products to consumers means not only understand-<br>ing their tastes, but also understanding their level of experience.<br>
For example, it would be a mistake to recommend the iconic film<br>Seven Samurai simply because a user enjoys other action movies;<br>rather, we might conclude that they will eventually enjoy it—once<br>they are ready. The same is true for beers, wines, gourmet foods—<br>
or any products where users have acquired tastes: the ‘best’ prod-<br>ucts may not be the most ‘accessible’. Thus our goal in this pa-<br>per is to recommend products that a user will enjoy now, while<br>acknowledging that their tastes may have changed over time, and<br>
may change again in the future. We model how tastes change due<br>to the very act of consuming more products—in other words, as<br>users become more experienced. We develop a latent factor rec-<br>ommendation system that explicitly accounts for each user’s level<br>
of experience. We find that such a model not only leads to better<br>recommendations, but also allows us to study the role of user expe-<br>rience and expertise on a novel dataset of fifteen million beer, wine,<br>food, and movie reviews.<br>
</i><br><br><br></div><br><div class=""><div id=":7jz" class="" tabindex="0"><img class="" src="https://mail.google.com/mail/u/0/images/cleardot.gif"></div></div><br>-- <br>Saiph Savage<br><br><br>
</div>