Physical Sciences and Mathematics Commons^™

Improving Multi-Label Emotion Classification Via Sentiment Classification With Dual Attention Transfer Network, Jianfei Yu, Luis Marujo, Jing Jiang, Pradeep Karuturi, William Brendel

Research Collection School Of Computing and Information Systems

In this paper, we target at improving the performance of multi-label emotion classification with the help of sentiment classification. Specifically, we propose a new transfer learning architecture to divide the sentence representation into two different feature spaces, which are expected to respectively capture the general sentiment words and the other important emotion-specific words via a dual attention mechanism. Extensive experimental results demonstrate that our transfer learning approach can outperform several strong baselines and achieve the state-of-the-art performance on two benchmark datasets.

Vpsearch: Achieving Verifiability For Privacy-Preserving Multi-Keyword Search Over Encrypted Cloud Data, Zhiguo Wan, Robert H. Deng

Research Collection School Of Computing and Information Systems

Although cloud computing offers elastic computation and storage resources, it poses challenges on verifiability of computations and data privacy. In this work we investigate verifiability for privacy-preserving multi-keyword search over outsourced documents. As the cloud server may return incorrect results due to system faults or incentive to reduce computation cost, it is critical to offer verifiability of search results and privacy protection for outsourced data at the same time. To fulfill these requirements, we design aVerifiablePrivacy-preserving keywordSearch scheme, called VPSearch, by integrating an adapted homomorphic MAC technique with a privacy-preserving multi-keyword search scheme. The proposed scheme enables the client to …

Latent Dirichlet Allocation For Textual Student Feedback Analysis, Swapna Gottipati, Venky Shankararaman, Jeff Lin

Research Collection School Of Computing and Information Systems

Education institutions collect feedback from students upon course completion and analyse it to improve curriculum design, delivery methodology and students' learning experience. A large part of feedback comes in the form textual comments, which pose a challenge in quantifying and deriving insights. In this paper, we present a novel approach of the Latent Dirichlet Allocation (LDA) model to address this difficulty in handling textual student feedback. The analysis of quantitative part of student feedback provides generalratings and helps to identify aspects of the teaching that are successful and those that can improve. The reasons for the failure or success, however, …

River: A Real-Time Influence Monitoring System On Social Media Stream, Mo Sha, Yuchen Li, Yanhao Wang, Wentian Guo, Kian-Lee Tan

Research Collection School Of Computing and Information Systems

Social networks generate a massive amount of interaction data among users in the form of streams. To facilitate social network users to consume the continuously generated stream and identify preferred viral social contents, we present a real-time monitoring system called River to track a small set of influential social contents from high-speed streams in this demo. River has four novel features which distinguish itself from existing social monitoring systems: (1) River extracts a set of contents which collectively have the most significant influence coverage while reducing the influence overlaps; (2) River is topic-based and monitors the contents which are relevant …

Unsupervised User Identity Linkage Via Factoid Embedding, Wei Xie, Xin Mu, Roy Ka Wei Lee, Feida Zhu, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

User identity linkage (UIL), the problem of matching user account across multiple online social networks (OSNs), is widely studied and important to many real-world applications. Most existing UIL solutions adopt a supervised or semisupervised approach which generally suffer from scarcity of labeled data. In this paper, we propose Factoid Embedding, a novel framework that adopts an unsupervised approach. It is designed to cope with different profile attributes, content types and network links of different OSNs. The key idea is that each piece of information about a user identity describes the real identity owner, and thus distinguishes the owner from other …

Linky: Visualizing User Identity Linkage Results For Multiple Online Social Networks (Demo), Roy Ka-Wei Lee, Ming Shan Hee, Philips Kokoh Prasetyo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

User identity linkage across online social networks is an emerging research topic that has attracted attention in recent years. Many user identity linkage methods have been proposed so far and most of them utilize user profile, content and network information to determine if two social media accounts belong to the same person. In most cases, user identity linkage methods are evaluated by performing some prediction tasks with the results presented using some overall accuracy measures. However, the methods are rarely compared at the individual user level where a predicted matched (or linked) pair of user identities from different online social …

Learning Generalized Video Memory For Automatic Video Captioning, Poo-Hee Chang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Recent video captioning methods have made great progress by deep learning approaches with convolutional neural networks (CNN) and recurrent neural networks (RNN). While there are techniques that use memory networks for sentence decoding, few work has leveraged on the memory component to learn and generalize the temporal structure in video. In this paper, we propose a new method, namely Generalized Video Memory (GVM), utilizing a memory model for enhancing video description generation. Based on a class of self-organizing neural networks, GVM’s model is able to learn new video features incrementally. The learned generalized memory is further exploited to decode the …

An Interpretable Neural Fuzzy Inference System For Predictions Of Underpricing In Initial Public Offerings, Di Wang, Xiaolin Qian, Chai Quek, Ah-Hwee Tan, Chunyan Miao, Xiaofeng Zhang, Geok See Ng, You Zhou

Research Collection School Of Computing and Information Systems

Due to their aptitude in both accurate data processing and human comprehensible reasoning, neural fuzzy inference systems have been widely adopted in various application domains as decision support systems. Especially in real-world scenarios such as decision making in financial transactions, the human experts may be more interested in knowing the comprehensive reasons of certain advices provided by a decision support system in addition to how confident the system is on such advices. In this paper, we apply an integrated autonomous computational model termed genetic algorithm and rough set incorporated neural fuzzy inference system (GARSINFIS) to predict underpricing in initial public …

Joint Representation Learning Of Cross-Lingual Words And Entities Via Attentive Distant Supervision, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Chengjiang Li, Xu Chen, Tiansi Dong

Research Collection School Of Computing and Information Systems

Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings. In this paper, we propose a novel method for joint representation learning of cross-lingual words and entities. It captures mutually complementary knowledge, and enables cross-lingual inferences among knowledge bases and texts. Our method does not require parallel corpora, and automatically generates comparable data via distant supervision using multi-lingual knowledge bases. We utilize two types of regularizers to align cross-lingual words and entities, and design knowledge attention and crosslingual attention to further reduce noises. We conducted a series of experiments on …

Building Iot Based Applications For Smart Cities: How Can Ontology Catalogs Help?, Amelia Gyrard, Antoine Zimmermann, Amit P. Sheth

Kno.e.sis Publications

The Internet of Things (IoT) plays an ever-increasing role in enabling smart city applications. An ontology-based semantic approach can help improve interoperability between a variety of IoT-generated as well as complementary data needed to drive these applications. While multiple ontology catalogs exist, using them for IoT and smart city applications require significant amount of work. In this paper, we demonstrate how can ontology catalogs be more effectively used to design and develop smart city applications? We consider four ontology catalogs that are relevant for IoT and smart cities: 1) READY4SmartCities; 2) linked open vocabulary (LOV); 3) OpenSensingCity (OSC); and 4) …

Exploiting The Interdependency Of Land Use And Mobility For Urban Planning, Kasthuri Jayarajah, Andrew Tan, Archan Misra

Research Collection School Of Computing and Information Systems

Urban planners and economists alike have strong interest in understanding the inter-dependency of land use and people flow. The two-pronged problem entails systematic modeling and understanding of how land use impacts crowd flow to an area and in turn, how the influx of people to an area (or lack thereof) can influence the viability of business entities in that area. With cities becoming increasingly sensor-rich, for example, digitized payments for public transportation and constant trajectory tracking of buses and taxis, understanding and modelling crowd flows at the city scale, as well as, at finer granularity such as at the neighborhood …

Geometry-Aware Similarity Learning On Spd Manifolds For Visual Recognition, Zhiwu Huang, R. Wang, X. Li, W. Liu, S. Shan, Gool L. Van, X Chen

Research Collection School Of Computing and Information Systems

Symmetric positive definite (SPD) matrices have been employed for data representation in many visual recognition tasks. The success is mainly attributed to learning discriminative SPD matrices encoding the Riemannian geometry of the underlying SPD manifolds. In this paper, we propose a geometry-aware SPD similarity learning (SPDSL) framework to learn discriminative SPD features by directly pursuing a manifold-manifold transformation matrix of full column rank. Specifically, by exploiting the Riemannian geometry of the manifolds of fixed-rank positive semidefinite (PSD) matrices, we present a new solution to reduce optimization over the space of column full-rank transformation matrices to optimization on the PSD manifold, …

Interpretable Multimodal Retrieval For Fashion Products, Lizi Liao, Xiangnan He, Bo Zhao, Chong-Wah Ngo, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Deep learning methods have been successfully applied to fashion retrieval. However, the latent meaning of learned feature vectors hinders the explanation of retrieval results and integration of user feedback. Fortunately, there are many online shopping websites organizing fashion items into hierarchical structures based on product taxonomy and domain knowledge. Such structures help to reveal how human perceive the relatedness among fashion products. Nevertheless, incorporating structural knowledge for deep learning remains a challenging problem. This paper presents techniques for organizing and utilizing the fashion hierarchies in deep learning to facilitate the reasoning of search results and user intent. The novelty of …

Knowledge-Aware Multimodal Dialogue Systems, Lizi Liao, Yunshan Ma, Xiangnan He, Richang Hong, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

By offering a natural way for information seeking, multimodal dialogue systems are attracting increasing attention in several domains such as retail, travel etc. However, most existing dialogue systems are limited to textual modality, which cannot be easily extended to capture the rich semantics in visual modality such as product images. For example, in fashion domain, the visual appearance of clothes and matching styles play a crucial role in understanding the user's intention. Without considering these, the dialogue agent may fail to generate desirable responses for users. In this paper, we present a Knowledge-aware Multimodal Dialogue (KMD) model to address the …

Using Electronic Health Records To Characterize Prescription Patterns: Focus On Antidepressants In Nonpsychiatric Outpatient Settings, Joseph J. Deferio, Tomer T. Levin, Judith Cukor, Samprit Banerjee, Rozan Abdulrahman, Amit P. Sheth, Neel Mehta, Jyotishman Pathak

Kno.e.sis Publications

Objective

To characterize nonpsychiatric prescription patterns of antidepressants according to drug labels and evidence assessments (on-label, evidence-based, and off-label) using structured outpatient electronic health record (EHR) data. Methods

A retrospective analysis was conducted using deidentified EHR data from an outpatient practice at a New York City-based academic medical center. Structured “medication–diagnosis” pairs for antidepressants from 35 325 patients between January 2010 and December 2015 were compared to the latest drug product labels and evidence assessments. Results

Of 140 929 antidepressant prescriptions prescribed by primary care providers (PCPs) and nonpsychiatry specialists, 69% were characterized as “on-label/evidence-based uses.” Depression diagnoses were associated …

Poster: Privacy-Preserving Boosting With Random Linear Classifiers, Sagar Sharma, Keke Chen

Kno.e.sis Publications

We propose SecureBoost, a privacy-preserving predictive modeling framework, that allows service providers (SPs) to build powerful boosting models over encrypted or randomly masked user submit- ted data. SecureBoost uses random linear classifiers (RLCs) as the base classifiers. A Cryptographic Service Provider (CSP) manages keys and assists the SP’s processing to reduce the complexity of the protocol constructions. The SP learns only the base models (i.e., RLCs) and the CSP learns only the weights of the base models and a limited leakage function. This separated parameter holding avoids any party from abusing the final model or conducting model-based attacks. We evaluate …

Traffic-Cascade: Mining And Visualizing Lifecycles Of Traffic Congestion Events Using Public Bus Trajectories, Agus Trisnajaya Kwee, Meng-Fen Chiang, Philips Kokoh Prasetyo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

As road transportation supports both economic and social activities in developed cities, it is important to maintain smooth traffic on all highways and local roads. Whenever possible, traffic congestions should be detected early and resolved quickly. While existing traffic monitoring dashboard systems have been put in place in many cities, these systems require high-cost vehicle speed monitoring instruments and detect traffic congestion as independent events. There is a lack of low-cost dashboards to inspect and analyze the lifecycle of traffic congestion which is critical in assessing the overall impact of congestion, determining the possible the source(s) of congestion and its …

Prediction Of Relatedness In Stack Overflow: Deep Learning Vs. Svm: A Reproducibility Study, Bowen Xu, Amirreza Shirani, David Lo, Mohammad Amin Alipour

Research Collection School Of Computing and Information Systems

Background Xu et al. used a deep neural network (DNN) technique to classify the degree of relatedness between two knowledge units (question-answer threads) on Stack Overflow. More recently, extending Xu et al.'s work, Fu and Menzies proposed a simpler classification technique based on a fine-tuned support vector machine (SVM) that achieves similar performance but in a much shorter time. Thus, they suggested that researchers need to compare their sophisticated methods against simpler alternatives.Aim The aim of this work is to replicate the previous studies and further investigate the validity of Fu and Menzies' claim by evaluating the DNN- and SVM-based …

Multiperspective Graph-Theoretic Similarity Measure, Dung D. Le, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Determining the similarity between two objects is pertinent to many applications. When the basis for similarity is a set of object-to-object relationships, it is natural to rely on graph-theoretic measures. One seminal technique for measuring the structural-context similarity between a pair of graph vertices is SimRank, whose underlying intuition is that two objects are similar if they are connected by similar objects. However, by design, SimRank as well as its variants capture only a single view or perspective of similarity. Meanwhile, in many real-world scenarios, there emerge multiple perspectives of similarity, i.e., two objects may be similar from one perspective, …

Ums Data Governance Annual Report 2018, University Of Maine System Data Advisory Committee

General University of Maine Publications

The newly formed University of Maine System Data Governance program was launched to improve the System's capacity to collect information and deploy resources in service to the students and in response to Maine's dire demographic and workforce challenges.

The UMS campuses and administrative units make up a complex system that requires a strategic approach to data collection and analysis. From understanding the intricacies of distance education and online programs, to aligning human resource and financial department codes, unified data governance is essential to ensuring the integrity and reliability of the University of Maine System's data.

Deep Understanding Of Cooking Procedure For Cross-Modal Recipe Retrieval, Jingjing Chen, Chong-Wah Ngo, Fu-Li Feng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Finding a right recipe that describes the cooking procedure for a dish from just one picture is inherently a difficult problem. Food preparation undergoes a complex process involving raw ingredients, utensils, cutting and cooking operations. This process gives clues to the multimedia presentation of a dish (e.g., taste, colour, shape). However, the description of the process is implicit, implying only the cause of dish presentation rather than the visual effect that can be vividly observed on a picture. Therefore, different from other cross-modal retrieval problems in the literature, recipe search requires the understanding of textually described procedure to predict its …

Sufat: An Analytics Tool For Gaining Insights From Student Feedback Comments, Siddhant Pyasi, Swapna Gottipati, Venky Shankararaman

Research Collection School Of Computing and Information Systems

Teacher evaluation is a vital element inimproving student learning outcomes. Course and instructor feedback given bystudents, provides insights that can help improve student learning outcomes andteaching quality. Teaching and course evaluation systems help to collectquantitative and qualitative feedback from students. Since manually analysingthe qualitative feedback is painstaking and a tedious process, usually, onlythe quantitative feedback is often used for evaluating the course and theinstructor. However, useful knowledge is hidden in the qualitative comments, inthe form of sentiments and suggestions that can provide valuable insights tohelp plan improvements in the course content and delivery. In order toefficiently gather, analyse and provide …

Inferring Trip Occupancies In The Rise Of Ride-Hailing Services, Meng-Fen Chiang, Ee-Peng Lim, Wang-Chien Lee, Tuan-Anh Hoang

Research Collection School Of Computing and Information Systems

The knowledge of all occupied and unoccupied trips made by self-employed drivers are essential for optimized vehicle dispatch by ride-hailing services (e.g., Didi Dache, Uber, Lyft, Grab, etc.). However, the occupancy status of vehicles is not always known to the service operators due to adoption of multiple ride-hailing apps. In this paper, we propose a novel framework, Learning to INfer Trips (LINT), to infer occupancy of car trips by exploring characteristics of observed occupied trips. Two main research steps, stop point classification and structural segmentation, are included in LINT. In the stop point classification step, we represent a vehicle trajectory …

Influence Maximization On Social Graphs: A Survey, Yuchen Li, Ju Fan, Yanhao Wang, Kian-Lee Tan

Research Collection School Of Computing and Information Systems

Influence Maximization (IM), which selects a set of k users (called seed set) from a social network to maximize the expected number of influenced users (called influence spread), is a key algorithmic problem in social influence analysis. Due to its immense application potential and enormous technical challenges, IM has been extensively studied in the past decade. In this paper, we survey and synthesize a wide spectrum of existing studies on IM from an algorithmic perspective, with a special focus on the following key aspects (1) a review of well-accepted diffusion models that capture information diffusion process and build the foundation …

A Learning And Masking Approach To Secure Learning, Linh Nguyen, Sky Wang, Arunesh Sinha

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed to fool the classifier. Such attacks can be devastating in practice, especially as DNNs are being applied to ever increasing critical tasks like image recognition in autonomous driving. In this paper, we introduce a new perspective on the problem. We do so by first defining robustness of a classifier to adversarial exploitation. Next, we show that the problem of adversarial example generation can be posed as learning problem. We also categorize attacks in literature into high and low perturbation attacks; well-known …

Optimal In-Place Suffix Sorting, Zhize Li, Jian Li, Hongwei Huo

Research Collection School Of Computing and Information Systems

The suffix array is a fundamental data structure for many applications that involve string searching and data compression. Designing time/space-efficient suffix array construction algorithms has attracted significant attentions and considerable advances have been made for the past 20 years. We obtain the first in-place linear time suffix array construction algorithms that are optimal both in time and space for (read-only) integer alphabets. Our algorithm settles the open problem posed by Franceschini and Muthukrishnan in ICALP 2007. The open problem asked to design in-place algorithms in $o(n \log n)$ time and ultimately, in $O(n)$ time for (read-only) integer alphabets with $|\Sigma| …

Interpretable Multimodal Retrieval For Fashion Products, Lizi Liao, Xiangnan He, Bo Zhao, Chong-Wah Ngo, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Deep learning methods have been successfully applied to fashion retrieval. However, the latent meaning of learned feature vectors hinders the explanation of retrieval results and integration of user feedback. Fortunately, there are many online shopping websites organizing fashion items into hierarchical structures based on product taxonomy and domain knowledge. Such structures help to reveal how human perceive the relatedness among fashion products. Nevertheless, incorporating structural knowledge for deep learning remains a challenging problem. This paper presents techniques for organizing and utilizing the fashion hierarchies in deep learning to facilitate the reasoning of search results and user intent. The novelty of …

Investigating Multimodal Affect Sensing In An Affective Tutoring System Using Unobtrusive Sensors, Hua Leong Fwa, Lindsay Marshall

Research Collection School Of Computing and Information Systems

Affect inextricably plays a critical role in the learning process. In this study, we investigate the multimodal fusion of facial, keystrokes, mouse clicks, head posture and contextual features for the detection of student’s frustration in an Affective Tutoring System. The results (AUC=0.64) demonstrated empirically that a multimodal approach offers higher accuracy and better robustness as compared to a unimodal approach. In addition, the inclusion of keystrokes and mouse clicks makes up for the detection gap where video based sensing modes (facial and head postures) are not available. The findings in this paper will dovetail to our end research objective of …

Interpretable Multimodal Retrieval For Fashion Products, Lizi Liao, Xiangnan He, Bo Zhao, Chong-Wah Ngo, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Deep learning methods have been successfully applied to fashion retrieval. However, the latent meaning of learned feature vectors hinders the explanation of retrieval results and integration of user feedback. Fortunately, there are many online shopping websites organizing fashion items into hierarchical structures based on product taxonomy and domain knowledge. Such structures help to reveal how human perceive the relatedness among fashion products. Nevertheless, incorporating structural knowledge for deep learning remains a challenging problem. This paper presents techniques for organizing and utilizing the fashion hierarchies in deep learning to facilitate the reasoning of search results and user intent. The novelty of …

Predicting Visual Context For Unsupervised Event Segmentation In Continuous Photo-Streams, Ana García Del Molino, Joo-Hwee Lim, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Segmenting video content into events provides semantic structures for indexing, retrieval, and summarization. Since motion cues are not available in continuous photo-streams, and annotations in lifelogging are scarce and costly, the frames are usually clustered into events by comparing the visual features between them in an unsupervised way. However, such methodologies are ineffective to deal with heterogeneous events, e.g. taking a walk, and temporary changes in the sight direction, e.g. at a meeting. To address these limitations, we propose Contextual Event Segmentation (CES), a novel segmentation paradigm that uses an LSTM-based generative network to model the photo-stream sequences, predict their …