In microblogging sites, recommending blogs (users) to follow is one of the core tasks for enhancing user experience. In this paper, we propose a novel inductive matrix completion based blog recommendation method to e ectively utilize multiple rich sources of evidence such as the social network and the content as well as the activity data from users and blogs. Experiments on a large-scale real-world dataset from Tumblr show the e ectiveness of the proposed blog recommendation method.
Tumblr1 is one of the most popular microblogging
services where users can create and share posts with the
followers of their blogs. Similar to Twitter2 and di erent from
Facebook3, connections in Tumblr are unidirectional. Unlike
Twitter, users can create longer, richer and higher quality
content in the form of several post types such as text, photo,
quote, link, chat, audio, and video [
One of the core problems in microblogging sites is
predicting whether a user will follow a blog or not. In addition to
the user-item interactions (user-item matrix), vast majority
of the existing work either used the social network
information or the textual content/pro les of users and items, and
did not e ectively utilize both types of information. A
recent comprehensive survey of the state-of-the-art methods
can be found in [
In this paper, we propose a novel inductive matrix
completion (IMC) based blog recommendation system that e
ectively utilizes the social network as well as the rich content
and activity (network) data from users and blogs in a
unied framework. Although, IMC has been shown to be highly
e ective in other domains such as bioinformatics (e.g., the
gene-disease association problem), it has not been utilized
for recommendation tasks [
Formally, let R 2 Rm n be the user-blog follower matrix,
where each row corresponds to a user and each column
corresponds to a blog, such that Rij = 1, if user i is following
blog j and 0 otherwise. The low rank matrix completion
approach is one of the most popular and successful
collaborative ltering methods for recommender systems [
(W HT )ij )2 + 2 (kW k2F + kHk2F ); where W 2 Rm r and H 2 Rn r with r being the dimension of the latent feature space; is the set of observed entries; is a regularization parameter.
However, the standard formulation is restricted to the
transductive setting, i.e., predictions can only be made to
existing users and items, and su ers performance with
extreme sparsity in the data. Recently, a novel inductive
matrix completion (IMC) approach was proposed by [
xiT W HT yj )2 + 2 (kW k2F + kHk2F ); where xi 2 Rfu and yj 2 Rfb are feature vectors for user i and item j, respectively (i.e., W 2 Rfu r and H 2 Rfb r). Given a new blog j, the predictions Rij for each user i can be calculated with the feature vector yj available. Note that the number of parameters to learn is (fu + fb) r, which depends only on the number of user and item features, whereas there is (m + n) r parameters in the standard matrix completion.
We evaluated IMC for blog recommendation, where
additional side information of both users and blogs are available.
We compare IMC against the standard matrix completion
formulation (MC) as well as the Singular Value
Decomposition (SVD), which has been shown to perform well for top-N
recommendation tasks [
For additional features, we use like, reblog, and tags
information collected over a period of 1 month from Tumblr.
Both like and reblog activities can be represented as a graph
similar to the follower graph R. One way to obtain useful
and robust features is to consider the principal components
of the adjacency matrix corresponding to the like and reblog
graphs. That is, we compute p principal components and
use them as latent user and blog features for IMC. For the
tags used in the posts of each blog, we rst compute vector
representations of each tag using the continuous skip-gram
model [
We measure the recommendation performance using the F1 score for the top-20 recommendations generated by each method, which is the region of partical interest for recommender systems. We also report the AUC (area under the curve) measured from the precision-vs-recall plot. Results of the proposed IMC method are shown in comparison to the baselines, Global, SVD, and MC for both metrics in Table 1. Note that we present normalized (relative) results in both metrics using the MC method as the baseline.
It is very interesting to see in Table 1 that the simple
Global method ourperforms both SVD and MC baselines.
This can be explained by the facts that most users follow
highly popular blogs such as institutions or celebrities [
Recommending blogs (users) to follow is one of the core tasks for enhancing user experience in online microblogging sites such as Tumblr. In addition to the social network information, it is very important to e ectively utilize the rich user and blog content (e.g., tags) as well as users' activities such as like and reblog. This paper proposes a novel inductive matrix completion based blog recommendation method that e ectively utilizes the social network as well as rich content and activity data from users and blogs. Experiments on large-scale real-world data from Tumblr show the e ectiveness of the proposed blog recommendation method.
Future work will mainly be conducted in i) utilizing
additional information from users and blogs such as the rich
visual features from posts in Tumblr as well as the (sparser)
textual features, and ii) using probabilistic latent-class or
mixed-membership approaches as shown in [