Quoc-Tuan Truong

I am a PhD candidate advised by Prof. Hady W. Lauw in School of Information Systems (SIS), Singapore Management University (SMU), and part of Preferred.AI research group. My research interests are in machine learning and data mining, focusing on multimodal sentiment analysis, preference learning and recommender systems.

I obtained my Bachelor's Degree in Computer Science from University of Engineering and Technology (UET), Vietnam National University, Hanoi (VNU). My thesis was on developing a mobile Virtual Assistant for Vietnamese (VAV), advised by Prof. Xuan-Hieu Phan.

Besides doing research, I enjoy developing open-source software and libraries as well as building machine learning applications. Currently, I am serving as an Intel Student Ambassador for Artificial Intelligence. Earlier on, I had the fortune to be one of the ten Vietnamese recipients of the Honda Y-E-S Award in 2016.

More about my publications: DBLP or Google Scholar

Selected Publications

Multimodal Review Generation for Recommender Systems
Quoc-Tuan Truong and Hady W. Lauw
The Web Conference (WWW'19), May 2019 (Long)
PDF | BibTeX | Code & Data

VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis
Quoc-Tuan Truong and Hady W. Lauw
AAAI Conference on Artificial Intelligence (AAAI'19), Jan 2019 (Long)
PDF | BibTeX | Code & Data

Visual Sentiment Analysis for Review Images with Item-Oriented and User-Oriented CNN
Quoc-Tuan Truong and Hady W. Lauw
ACM Multimedia (MM'17), Oct 2017 (Long)
PDF | BibTeX | Code & Data | Blog 1, 2

We observe that the sentiment captured within an image may be affected by three factors: image factor, user factor, and item factor. Essentially, only the first factor had been taken into account by previous works on visual sentiment analysis. Thus, we develop item-oriented and user-oriented Convolutional Neural Networks (CNN) that better capture the interaction of image features with specific expressions of users or items.

Last updated in Feb 2020.