Learn More
Although users' preference is semantically reflected in the free-form review texts, this wealth of information was not fully exploited for learning recommender models. Specifically, almost all existing recommendation algorithms only exploit rating scores in order to find users' preference, but ignore the review texts accompanied with rating information. In(More)
Trust has been used to replace or complement rating-based similarity in recommender systems, to improve the accuracy of rating prediction. However, people trusting each other may not always share similar preferences. In this paper, we try to fill in this gap by decomposing the original single-aspect trust information into four general trust aspects, i.e.(More)
AIM To compare the fast-track rehabilitation program and conventional care for patients after resection of colorectal cancer. METHODS One hundred and six consecutive patients who underwent fast-track rehabilitation program were encouraged to have early oral feeding and movement for early discharge, while 104 consecutive patients underwent conventional(More)
This study was devised to investigate whether fibrin glue (FG) in combination with growth hormone (GH) could have a beneficial effect at a late period (14 days) after injury. Male Wistar rats, with abdominal sepsis induced by an incomplete anastomosis, were divided into three groups. In the control group, the rats got incomplete anastomoses sutured alone;(More)
OBJECTIVE To evaluate the safety, feasibility, and efficacy of robotic gastrectomy for gastric cancer using da Vinci surgical system. METHODS A total of 120 patients who underwent robotic gastrectomy using da Vinci surgical system for gastric cancer from May 2010 to April 2012. Data regarding surgical and early oncological outcomes were systematically(More)
Cross-domain text classification aims to automatically train a precise text classifier for a target domain by using labelled text data from a related source domain. To this end, one of the most promising ideas is to induce a new feature representation so that the distributional difference between domains can be reduced and a more accurate classifier can be(More)
It is indispensable for users to evaluate the trust-worthiness of other users (referred to as advisors), to cope with possible misleading opinions provided by them. Advisors' misleading opinions may be induced by their dishonesty, subjectivity difference with users, or both. Existing approaches do not well distinguish the two different causes. In this(More)
In this paper, we propose a novel problem of summarizing textual corporate risk factor disclosure, which aims to simultaneously infer the risk types across corpus and assign each risk factor to its most probable risk type. To solve the problem, we develop a variation of LDA topic model called Sent-LDA. The variational EM learning algorithm, which guarantees(More)