Databases and Information Systems Commons^™

On Effective Personalized Music Retrieval Via Exploring Online User Behaviors, Zhiyong Cheng, Jialie Shen, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

In this paper, we study the problem of personalized text based music retrieval which takes users' music preferences on songs into account via the analysis of online listening behaviours and social tags. Towards the goal, a novel Dual-Layer Music Preference Topic Model (DL-MPTM) is proposed to construct latent music interest space and characterize the correlations among (user, song, term). Based on the DL-MPTM, we further develop an effective personalized music retrieval system. To evaluate the system's performance, extensive experimental studies have been conducted over two test collections to compare the proposed method with the state-of-the-art music retrieval methods. The results …

Where Is The Goldmine? Finding Promising Business Locations Through Facebook Data Analytics, Jovian Lin, Richard Oentaryo, Ee-Peng Lim, Casey Vu, Adrian Vu, Agus Kwee

Research Collection School Of Computing and Information Systems

If you were to open your own cafe, would you not want to effortlessly identify the most suitable location to set up your shop? Choosing an optimal physical location is a critical decision for numerous businesses, as many factors contribute to the final choice of the location. In this paper, we seek to address the issue by investigating the use of publicly available Facebook Pages data-which include user "check-ins", types of business, and business locations-to evaluate a user-selected physical location with respect to a type of business. Using a dataset of 20,877 food businesses in Singapore, we conduct analysis of …

On Very Large Scale Test Collection For Landmark Image Search Benchmarking, Zhiyong Cheng, Jialie Shen

Research Collection School Of Computing and Information Systems

High quality test collections have been becoming more and more important for the technological advancement in geo-referenced image retrieval and analytics. In this paper, we present a large scale test collection to support robust performance evaluation of landmark image search and corresponding construction methodology. Using the approach, we develop a very large scale test collection consisting of three key components: (1) 355,141 images of 128 landmarks in five cities across three continents crawled from Flickr; (2) different kinds of textual features for each image, including surrounding text (e.g. tags), contextual data (e.g. geo-location and upload time), and metadata (e.g. uploader …

Which Information Sources Are More Effective And Reliable In Video Search, Cheng Zhiyong, Xuanchong Li, Jialie Shen, Alexander G. Hauptmann

Research Collection School Of Computing and Information Systems

It is common that users are interested in finding video segments, which contain further information about the video contents in a segment of interest. To facilitate users to find and browse related video contents, video hyperlinking aims at constructing links among video segments with relevant information in a large video collection. In this study, we explore the effectiveness of various video features on the performance of video hyperlinking, including subtitle, metadata, content features (i.e., audio and visual), surrounding context, as well as the combinations of those features. Besides, we also test different search strategies over different types of queries, which …

Can Instagram Posts Help Characterize Urban Micro-Events?, Kasthuri Jayarajah, Archan Misra

Research Collection School Of Computing and Information Systems

Social media content, from platforms such as Twitter and Foursquare, has enabled an exciting new field of social sensing, where participatory content generated by users has been used to identify unexpected emerging or trending events. In contrast to such text-based channels, we focus on image-sharing social applications (specifically Instagram), and investigate how such urban social sensing can leverage upon the additional multi-modal, multimedia content. Given the significantly higher fraction of geotagged content on Instagram, we aim to use such channels to go beyond identification of long-lived events (e.g., a marathon) to achieve finer-grained characterization of multiple micro-events (e.g., a person …

The Impact Of Security Cues On User Perceived Security In E-Commerce, Samuel N. Smith, Fiona Fui-Hoon Nah, Maggie X. Cheng

Research Collection School Of Computing and Information Systems

Users are expected to assess the level of security of e-commerce websites before conducting online transactions. In this research, we examine user assessment of security of e-commerce web pages based on cues presented on the web pages. A pilot study was conducted in which each subject assessed six e-commerce web pages with varying cues (i.e., HTTP vs. HTTPS, fraudulent vs. authentic URL, padlocks beside fields), and the findings are reported.

Learning Compact Visual Representation With Canonical Views For Robust Mobile Landmark Search, Lei Zhu, Jialie Shen, Xiaobai Liu, Liang Xie, Liqiang Nie

Research Collection School Of Computing and Information Systems

Mobile Landmark Search (MLS) recently receives increasing attention. However, it still remains unsolved due to two important issues. One is high bandwidth consumption of query transmission, and the other is the huge visual variations of query images. This paper proposes a Canonical View based Compact Visual Representation (2CVR) to handle these problems via novel three-stage learning. First, a submodular function is designed to measure visual representativeness and redundancy of a view set. With it, canonical views, which capture key visual appearances of landmark with limited redundancy, are efficiently discovered with an iterative mining strategy. Second, multimodal sparse coding is applied …

The Impact Of Nasd Rule 2711 And Nyse Rule 472 On Analyst Behavior: The Strategic Timing Of Recommendations Issued On Weekends, Yi Dong, Nan Hu

Research Collection School Of Computing and Information Systems

Amendments to NASD Rule 2711 and NYSE Rule 472, enacted in May 2002, mandate that sell-side analysts disclose the distribution of their security recommendations by buy, hold and sell category. This regulation enhances the transparency of analysts' information and mitigates the long-recognized optimistic bias in their recommendations. However, we find that analysts are more likely to issue sell recommendations or downgrade revisions on weekends when investors have limited attention after these rule changes. This pattern is more pronounced for prestigious analysts, who are more likely to influence stock prices. Market reaction tests reveal an incomplete immediate response and a greater …

Outlier Detection In Complex Categorical Data By Modeling The Feature Value Couplings, Guansong Pang, Longbing Cao, Ling Chen

Research Collection School Of Computing and Information Systems

This paper introduces a novel unsupervised outlier detection method, namely Coupled Biased Random Walks (CBRW), for identifying outliers in categorical data with diversified frequency distributions and many noisy features. Existing pattern-based outlier detection methods are ineffective in handling such complex scenarios, as they misfit such data. CBRW estimates outlier scores of feature values by modelling feature value level couplings, which carry intrinsic data characteristics, via biased random walks to handle this complex data. The outlier scores of feature values can either measure the outlierness of an object or facilitate the existing methods as a feature weighting and selection indicator. Substantial …

Real-Time Salient Object Detection With A Minimum Spanning Tree, Wei-Chih Tu, Shengfeng He, Qingxiong Yang, Shao-Yi Chien

Research Collection School Of Computing and Information Systems

In this paper, we present a real-time salient object detection system based on the minimum spanning tree. Due to the fact that background regions are typically connected to the image boundaries, salient objects can be extracted by computing the distances to the boundaries. However, measuring the image boundary connectivity efficiently is a challenging problem. Existing methods either rely on superpixel representation to reduce the processing units or approximate the distance transform. Instead, we propose an exact and iteration free solution on a minimum spanning tree. The minimum spanning tree representation of an image inherently reveals the object geometry information in …

Patient Engagement In The Medical Facility Waiting Room Using Gamified Healthcare Information Delivery, Raheel Hassan, Nathan W. Twyman, Fiona F. Nah, Keng Siau

Research Collection School Of Computing and Information Systems

This study explores the proposition that medical facility waiting rooms are an opportune setting to engage with and educate patients while they are waiting for care. In collaboration with emergency department (ED) personnel, we developed ER Hero, a tablet-based application for waiting rooms that introduces patients to ED professionals and operations through mini-games and story-like interaction. We evaluated this prototype with human participants to determine how well it performed when compared to paper-based information disclosure presenting the same information. Participants using the application exhibited increased ED knowledge, decreased nervousness, and increased interest. The gamified application outperformed a paper-based approach on …

Self-Regulated Incremental Clustering With Focused Preferences, Di Wang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Due to their online learning nature, incremental clustering techniques can handle a continuous stream of data. In particular, various incremental clustering techniques based on Adaptive Resonance Theory (ART) have been shown to have low computational complexity in adaptive learning and are less sensitive to noisy information. However, parameter regularization in existing ART clustering techniques is applied either on different features or on different clusters exclusively. In this paper, we introduce Interest-Focused Clustering based on Adaptive Resonance Theory (IFC-ART), which self-regulates the vigilance parameter associated with each feature and each cluster. As such, we can incorporate the domain knowledge of the …

Hci Testing In Laboratory Or Field Settings, Chuan-Hoo Tan, Austin Silva, Rich Lee, Kanliang Wang, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

This paper presents perspectives from both academia and practice on how an HCI testing is to be conducted and the deliberations that go into the testing. HCI testing can be conducted in closed-door laboratory or in a field setting. While there is an increased interest in field testing of an HCI artifact, there is always an enduring concern over how to administer a field testing given that the testers will have less control over the course of testing. In this paper, we cover HCI testing deliberation as well as the operational issues of field testing, and conclude the paper with …

The Effects Of Multiple Query Evidences On Social Image Retrieval, Zhiyong Cheng, Jialie Shen, Haiyan Miao

Research Collection School Of Computing and Information Systems

System performance assessment and comparison are fundamental for large-scale image search engine development. This article documents a set of comprehensive empirical studies to explore the effects of multiple query evidences on large-scale social image search. The search performance based on the social tags, different kinds of visual features and their combinations are systematically studied and analyzed. To quantify the visual query complexity, a novel quantitative metric is proposed and applied to assess the influences of different visual queries based on their complexity levels. Besides, we also study the effects of automatic text query expansion with social tags using a pseudo …

Blind And Visually Impaired Users Adaptation To Web Environments: A Qualitative Study, Raneem Saqr

USF Tampa Graduate Theses and Dissertations

Although much research exists on human behavior in online environments, research on users with disabilities is still rare. To draw more attention to this population, this dissertation explored browsing patterns and adaptive behaviors of people with visual disability across different online environments common in daily activities: social network, e-commerce, online information, and search engines’ websites. The main objective of this study is to propose a conceptual framework of how blind and visually impaired users browse and adapt to different web environments. We achieve this objective using a qualitative approach through three studies. In the first study, the researchers collect data …

Analyze Large Multidimensional Datasets Using Algebraic Topology, David Le

Master's Projects

This paper presents an efficient algorithm to extract knowledge from high-dimensionality, high- complexity datasets using algebraic topology, namely simplicial complexes. Based on concept of isomorphism of relations, our method turn a relational table into a geometric object (a simplicial complex is a polyhedron). So, conceptually association rule searching is turned into a geometric traversal problem. By leveraging on the core concepts behind Simplicial Complex, we use a new technique (in computer science) that improves the performance over existing methods and uses far less memory. It was designed and developed with a strong emphasis on scalability, reliability, and extensibility. This paper …

Musictrakr, Benjamin Lin

Computer Engineering

MusicTrackr is an IoT device that musicians attach to their instruments. The device has a start and stop button that allows users to record their playing sessions. Each recorded session is sent wirelessly to a cloud database. An accompanying website displays all of the recorded sessions, organized by date. After picking a specific date, the user can view graphs showing total practice time and average session length as well play back any recordings during that date. In addition, the user may add comments to any specific date or recording. Lastly, the user may tag a specific date with a color …

Link Prediction In A Weighted Network Using Support Vector Machine, Jan Miles Co, Proceso L. Fernandez Jr

Department of Information Systems & Computer Science Faculty Publications

Link prediction is a field under network analysis that deals with the existence or emergence of links. In this study, we investigate the effect of using weighted networks for two link prediction techniques, which are the Vector Auto Regression (VAR) technique and our proposed modified VAR that uses Support Vector Machine (SVM). Using a co-authorship network from DBLP as the dataset and the Area Under the Receiver Operating Curve (AUC-ROC) as the fitness metric, the results show that the performance of both VAR and SVM are surprisingly lower in the weighted network than in the unweighted network. In an attempt …

User Behavior Mining In Microblogging, Tuan Anh Hoang

Dissertations and Theses Collection (Open Access)

This dissertation addresses the modeling of factors concerning microblogging users' content and behavior. We focus on two sets of factors. The first set includes behavioral factors of users and content items driving content propagation in microblogging. The second set consists of latent topics and communities of users as the users are engaged in content generation and behavior adoptions. These two sets of factors are extremely important in many applications, e.g., network monitoring and recommender systems. In the first part of this dissertation, we identify user virality, user susceptibility, and content virality as three behavioral factors that affect users' behaviors in …

Skewer: Sentiment Knowledge Extraction With Entity Recognition, Christopher James Wu

Master's Theses

The California state legislature introduces approximately 5,000 new bills each legislative session. While the legislative hearings are recorded on video, the recordings are not easily accessible to the public. The lack of official transcripts or summaries also increases the effort required to gain meaningful insight from those recordings. Therefore, the news media and the general population are largely oblivious to what transpires during legislative sessions.

Digital Democracy, a project started by the Cal Poly Institute for Advanced Technology and Public Policy, is an online platform created to bring transparency to the California legislature. It features a searchable database of state …