• Publications
  • Influence
On social networks and collaborative recommendation
TLDR
This work created a collaborative recommendation system that effectively adapts to the personal information needs of each user, and adopts the generic framework of Random Walk with Restarts in order to provide with a more natural and efficient way to represent social networks.
Building a large-scale corpus for evaluating event detection on twitter
TLDR
A methodology for the creation of an event detection corpus is proposed, which makes use of existing state-of-the-art event detection approaches and Wikipedia to generate a set of candidate events with associated tweets and uses crowdsourcing to gather relevance judgements.
A Simple Convolutional Generative Network for Next Item Recommendation
TLDR
A simple, but very effective generative model that is capable of learning high-level representation from both short- and long-range item dependencies is introduced that attains state-of-the-art accuracy with less training time in the next item recommendation task.
Personalizing Web Search with Folksonomy-Based User and Document Profiles
TLDR
This paper proposes to represent a user profile in terms of social tags, manually provided by users in folksonomy systems to describe, categorize and organize items of interest, and investigates a number of novel techniques that exploit the users’ social tags to re-rank results obtained with a Web search engine.
Real-Time Entity-Based Event Detection for Twitter
TLDR
It is found that nouns and verbs play different roles in event detection and that the use of hashtags and retweets lead to a decreases in effectiveness when using the entity-base approach.
Text segmentation via topic modeling: an analytical study
TLDR
The use of latent Dirichlet allocation (LDA) topic model to segment a text into semantically coherent segments is investigated and yields significantly better performance than most of the available unsupervised methods on a benchmark dataset.
Relational Collaborative Filtering: Modeling Multiple Item Relations for Recommendation
TLDR
This work proposes Relational Collaborative Filtering (RCF) to exploit multiple item relations in recommender systems, and finds that both the relation type and the relation value are crucial in inferring user preference.
CFM: Convolutional Factorization Machines for Context-Aware Recommendation
TLDR
Con Convolutional Factorization Machine (CFM) is proposed, which models second-order interactions with outer product, resulting in "images" which capture correlations between embedding dimensions, and 3D convolution is applied above it to learn high-order interaction signals in an explicit approach.
Recent and robust query auto-completion
TLDR
Several practical completion suggestion ranking approaches are proposed, including a sliding window of query popularity evidence from the past 2-28 days, and the query popularity distribution in the last N queries observed with a given prefix, and short-range query popularity prediction based on recently observed trends.
...
...