Digital Commons Network^™

She Elicits Requirements And He Tests: Software Engineering Gender Bias In Large Language Models, Christoph Treude, Hideaki Hata

Research Collection School Of Computing and Information Systems

Implicit gender bias in software development is a well-documented issue, such as the association of technical roles with men. To address this bias, it is important to understand it in more detail. This study uses data mining techniques to investigate the extent to which 56 tasks related to software development, such as assigning GitHub issues and testing, are affected by implicit gender bias embedded in large language models. We systematically translated each task from English into a genderless language and back, and investigated the pronouns associated with each task. Based on translating each task 100 times in different permutations, we …

Two Sides Of The Same Coin: Exploiting The Impact Of Identifiers In Neural Code Comprehension, Shuzheng Gao, Cuiyun Gao, Chaozheng Wang, Jun Sun, David Lo, Yue Yu

Research Collection School Of Computing and Information Systems

Previous studies have demonstrated that neural code comprehension models are vulnerable to identifier naming. By renaming as few as one identifier in the source code, the models would output completely irrelevant results, indicating that identifiers can be misleading for model prediction. However, identifiers are not completely detrimental to code comprehension, since the semantics of identifier names can be related to the program semantics. Well exploiting the two opposite impacts of identifiers is essential for enhancing the robustness and accuracy of neural code comprehension, and still remains under-explored. In this work, we propose to model the impact of identifiers from a …

Fine-Grained Commit-Level Vulnerability Type Prediction By Cwe Tree Structure, Shengyi Pan, Lingfeng Bao, Xin Xia, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

Identifying security patches via code commits to allow early warnings and timely fixes for Open Source Software (OSS) has received increasing attention. However, the existing detection methods can only identify the presence of a patch (i.e., a binary classification) but fail to pinpoint the vulnerability type. In this work, we take the first step to categorize the security patches into fine-grained vulnerability types. Specifically, we use the Common Weakness Enumeration (CWE) as the label and perform fine-grained classification using categories at the third level of the CWE tree. We first formulate the task as a Hierarchical Multi-label Classification (HMC) problem, …

A Study Of Variable-Role-Based Feature Enrichment In Neural Models Of Code, Aftab. Hussain, Md. Rafiqul Islam. Rabin, Bowen. Xu, David Lo, Mohammad Amin. Alipour

Research Collection School Of Computing and Information Systems

Although deep neural models substantially reduce the overhead of feature engineering, the features readily available in the inputs might significantly impact training cost and the performance of the models. In this paper, we explore the impact of an unsuperivsed feature enrichment approach based on variable roles on the performance of neural models of code. The notion of variable roles (as introduced in the works of Sajaniemi et al. [1], [2]) has been found to help students' abilities in programming. In this paper, we investigate if this notion would improve the performance of neural models of code. To the best of …

Semparser: A Semantic Parser For Log Analytics, Yintong Huo, Yuxin Su, Cheryl Lee, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Logs, being run-time information automatically generated by software, record system events and activities with their timestamps. Before obtaining more insights into the run-time status of the software, a fundamental step of log analysis, called log parsing, is employed to extract structured templates and parameters from the semi-structured raw log messages. However, current log parsers are all syntax-based and regard each message as a character string, ignoring the semantic information included in parameters and templates.Thus, we propose the first semantic-based parser SemParser to unlock the critical bottleneck of mining semantics from log messages. It contains two steps, an end-to-end semantics miner …

On-Device Deep Multi-Task Inference Via Multi-Task Zipping, Xiaoxi He, Xu Wang, Zimu Zhou, Jiahang Wu, Zheng Yang, Lothar Thiele

Research Collection School Of Computing and Information Systems

Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks locally on-device. Yet the complexity of these deep models needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory. Previous studies squeeze the redundancy within a single model. In this work, we aim to reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to automatically merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme …

Essays On Operations Management Problems In Service And Retail Systems, Ruijie Zhang

Dissertations and Theses Collection (Open Access)

Customers' waiting experiences are crucial in service and retail systems, and this thesis investigates their impact in various contexts. In the service system, long waiting time causes customers' no-show behavior, and negative feedback from existing customers, which in turn results in low conversion and loss of revenue for service providers. However, waiting is not always a negative presence. In the online retail system, with the innovation of the sales model, long waiting can earn more time for online retailers to ease the logistics pressure although it may reduce customers' willingness to pay at the same time. Against this backdrop, in …

Consumer Reaction To The Use Of Artificial Intelligence Chatbot On Distribution Of General Insurance In Singapore, Lai Hing Tan

Dissertations and Theses Collection (Open Access)

As technology rapidly permeates all aspects of our lives, it is not unusual to question and even challenge the rationale on why certain industries are slower to adapt to the new digital age. Insurance is a business that is under scrutiny given its traditional ways of selling and legacy challenges. Why is technology investment in insurance companies lagging others? One emerging technological disruption is artificial intelligence (AI). It is the science of designing and building intelligent systems that can complete tasks traditionally performed by humans. AI is expected to fundamentally transform today’s marketplace, for businesses and consumers alike. However, because …

Does Watching Videos With Natural Scenery Restore Attentional Resources? A Critical Examination Through A Pre-Registered Within-Subject Experiment, Andree Hartanto, Nicole Lee Anne Teo, Verity Y. Q. Lua, Keith Tay, Nicole R. Y. Chen, Nadyanna M. Majeed

Research Collection School of Social Sciences

Existing studies have shown that direct exposure to a real nature environment has a restorative effect on attentional resources after a mentally fatiguing task. However, it remains unclear whether virtual nature simulations can serve as a substitute for real nature experienced in the outdoors to restore executive attention. Given the mixed findings in the literature, the present study sought to examine if viewing videos with natural scenery (vs. a control with urban scenery) restores participants’ working memory capacity – measured by an operation span task – in a high-powered pre-registered within-subject experimental study. Overall, our within-subject experiment did not find …

To Ask Better Questions, Teach: Learning-By-Teaching Enhances Research Question Generation More Than Retrieval Practice And Concept-Mapping, Sarah Shi Hui Wong, Kagen Y. L. Lim, Stephen Wee Hun Lim

Research Collection School of Social Sciences

Asking good questions is vital for scientific learning and discovery, but improving this complex skill is a formidable challenge. Here, we show in two experiments (N = 152) that teaching others—learning-by-teaching—enhances one’s ability to generate higher-order research questions that create new knowledge, relative to two other well-established generative learning techniques: retrieval practice and concept-mapping. Learners who taught scientific expository texts across natural and social sciences topics by delivering video-recorded lectures outperformed their peers who practiced retrieval or constructed concept maps when tested on their ability to generate create-level research questions based on the texts (Experiment 1). This advantage held reliably …

Algorithms, Leadership, And Morality: Why A Mere Human Effect Drives The Preference For Human Over Algorithmic Leadership, Jack Mcguire, David De Cremer

Research Collection Lee Kong Chian School Of Business

Algorithms are increasingly making decisions in organizations that carry moral consequences and such decisions are considered to be ordinarily made by leaders. An important consideration to be made by organizations is therefore whether adopting algorithms in this domain will be accepted by employees and whether this practice will harm their reputation. Considering this emergent phenomenon, we set out to examine employees’ perceptions about (a) algorithmic decision-making systems employed to occupy leadership roles and make moral decisions in organizations, and (b) the reputation of organizations that employ such systems. Furthermore, we examine the extent to which the decision agent needs to …

The Persuasive Design Of Ai-Synthesized Voices, Hannah H. Chang, Anirban Mukherjee

Research Collection Lee Kong Chian School Of Business

We investigate the impact of AI-based, machine-synthesized narrating voices on consumer cognitions and behavior in media-rich environment. Across four studies (plus pretests), we show that the design of AI voices systematically and predictably affects consumer cognition and behavior. Specifically, the designs of AI voices have differential effects in early versus later stages of consumer purchase journey. In situations where the consumers’ attention is already directed to the message, we find that marcomm with more AI voices generates a smaller proportion of favorable thoughts, which leads to a lower purchase likelihood. These results support our conceptualization that hearing more AI voices …

Moving Towards Principles-Based Accounting Standards: The Impact Of The New Revenue Standard On The Quality Of Accrual Accounting, He, Huiyu

Dissertations and Theses Collection (Open Access)

The new revenue standard (ASU 2014-09, codified in ASC 606 and ASC 340-40) establishes a comprehensive framework on accounting for contracts with customers and replaces most existing revenue recognition rules. The new guidance removes the inconsistencies and weaknesses of legacy guidance, while is more principles-based and requires more managerial judgements. Using as-reported data from structured filings to construct aggregate accruals that are potentially affected by the new revenue standard (i.e., sales-related accruals), I find that the new revenue standard increases the quality of sales-related accruals, as measured by future cash flow predictability. The increased cash flow predictability comes not only …

Connecting The Dots For Contextual Information Retrieval, Pei-Chi Lo

Dissertations and Theses Collection (Open Access)

There are many information retrieval tasks that depend on knowledge graphs to return contextually relevant result of the query. We call them Knowledgeenriched Contextual Information Retrieval (KCIR) tasks and these tasks come in many different forms including query-based document retrieval, query answering and others. These KCIR tasks often require the input query to contextualized by additional facts from a knowledge graph, and using the context representation to perform document or knowledge graph retrieval and prediction. In this dissertation, we present a meta-framework that identifies Contextual Representation Learning (CRL) and Contextual Information Retrieval (CIR) to be the two key components in …

Document Graph Representation Learning, Ce Zhang

Dissertations and Theses Collection (Open Access)

Much of the data on the Web can be represented in a graph structure, ranging from social and biological to academic and Web page graphs, etc. Graph analysis recently attracts escalating research attention due to its importance and wide applicability. Diverse problems could be formulated as graph tasks, such as text classification and information retrieval. As the primary information is the inherent structure of the graph itself, one promising direction known as the graph representation learning problem is to learn the representation of each node, which could in turn fuel tasks such as node classification, node clustering, and link prediction. …

Learning Dynamic Multimodal Networks, Meng Kiat Gary Ang

Dissertations and Theses Collection (Open Access)

Capturing and modeling relationship networks consisting of entity nodes and attributes associated with these nodes is an important research topic in network or graph learning. In this dissertation, we focus on modeling an important class of networks present in many real-world domains. These networks involve i) attributes from multiple modalities, also known as multimodal attributes; ii) multimodal attributes that are not static but time-series information, i.e., dynamic multimodal attributes, and iii) relationships that evolve across time, i.e., dynamic networks. We refer to such networks as dynamic multimodal networks in this dissertation.

An example of a static multimodal network is one …

Driving Forces Of Mining Outsourcing: Evidence From China, Bingxu Zheng

Dissertations and Theses Collection (Open Access)

The outsourcing of services by mining enterprises has become a significant global trend. Classic studies have demonstrated that outsourcing can help enterprises obtain professional services, improving productivity and reducing production costs. However, as a transitional economy, China has its unique characteristics regarding the driving forces of service outsourcing. By employing a case study method, one mining service outsourcing provider, and five mining enterprises' interviews and archival data, this study constructs a theory to identify the driving forces and mechanisms of mining enterprises' choice of service outsourcing and a logic relationship between variables via a diagram.

The case study results reveal …

On The Spectral Density Of Fractional Ornstein-Uhlenbeck Process: Approximation, Estimation, And Model Comparison, Shuping Shi, Jun Yu, Chen Zhang

Research Collection School Of Economics

This paper introduces a novel method for accurately approximating the spectral density of the discretely-sampled fractional Ornstein-Uhlenbeck (fOU) process. We utilize this approximated spec-tral density to develop an estimation method called the approximated Whittle maximum likelihood method (AWML) for fOU. Additionally, we develop a likelihood-ratio (LR) test using the approxi-mated spectral densities to distinguish between the fractional Brownian motion (fBm) and fOU pro-cesses, two popular models in the volatility literature. Simulation studies demonstrate that the AWML method improves the estimation speed and accuracy compared to existing ones and that the LR test is effective in distinguishing between the two processes …

Teaching In The Right Context: Textbook Supply Program, Language, And Vocabulary Ability In Vietnam, Tomoki Fujii, Maki Nakajima, Sijia Xu

Research Collection School Of Economics

An ethnic gap in education is prevalent around the world. This remains the case in Vietnam, a country that has achieved phenomenal economic growth and raised the educational attainment of the public. This paper examines the impact of language policy reorientation represented by the textbook supply program in Vietnam on the ethnic gap in children's learning measured by a vocabulary test. Applying difference-in-differences estimation to the Young Lives data between 2006 and 2015, we show that the program became more effective in narrowing the ethnic gap as the education policy became reoriented toward ethnic minority children. A causal mediation analysis …

Picaso: Enhancing Api Recommendations With Relevant Stack Overflow Posts, Ivana Clairine Irsan, Ting Zhang, Ferdian Thung, Kisub Kim, David Lo

Research Collection School Of Computing and Information Systems

While having options could be liberating, too many options could lead to the sub-optimal solution being chosen. This is not an exception in the software engineering domain. Nowadays, API has become imperative in making software developers' life easier. APIs help developers implement a function faster and more efficiently. However, given the large number of open-source libraries to choose from, choosing the right APIs is not a simple task. Previous studies on API recommendation leverage natural language (query) to identify which API would be suitable for the given task. However, these studies only consider one source of input, i.e., GitHub or …

Applying Information Theory To Software Evolution, Adriano Torres, Sebastian Baltes, Christoph Treude, Markus Wagner

Research Collection School Of Computing and Information Systems

Although information theory has found success in disciplines, the literature on its applications to software evolution is limit. We are still missing artifacts that leverage the data and tooling available to measure how the information content of a project can be a proxy for its complexity. In this work, we explore two definitions of entropy, one structural and one textual, and apply it to the historical progression of the commit history of 25 open source projects. We produce evidence that they generally are highly correlated. We also observed that they display weak and unstable correlations with other complexity metrics. Our …

Re-Evaluating Natural Intelligence In The Face Of Chatgpt, Elvin T. Lim, Tze K Koh

Research Collection College of Integrative Studies

How will new technologies impact the nature of higher education? Before ChatGPT, the world witnessed major shifts led by innovations in information storage and transmission. Papyrus in ancient Egypt, the Gutenberg press in 15th-century Europe, and the internet in the 20th century were all milestones in the mass dissemination of knowledge.

Learning-Based Stock Trending Prediction By Incorporating Technical Indicators And Social Media Sentiment, Zhaoxia Wang, Zhenda Hu, Fang Li, Seng-Beng Ho, Erik Cambria

Research Collection School Of Computing and Information Systems

Stock trending prediction is a challenging task due to its dynamic and nonlinear characteristics. With the development of social platform and artificial intelligence (AI), incorporating timely news and social media information into stock trending models becomes possible. However, most of the existing works focus on classification or regression problems when predicting stock market trending without fully considering the effects of different influence factors in different phases. To address this gap, this research solves stock trending prediction problem utilizing both technical indicators and sentiments of the social media text as influence factors in different situations. A 3-phase hybrid model is proposed …

Liloc: Enabling Precise 3d Localization In Dynamic Indoor Environments Using Lidars, Darshana Rathnayake, Meera Radhakrishnan, Inseok Hwang, Archan Misra

Research Collection School Of Computing and Information Systems

We present LiLoc, a system for precise 3D localization and tracking of mobile IoT devices (e.g., robots) in indoor environments using multi-perspective LiDAR sensing. The key differentiators in our work are: (a) First, unlike traditional localization approaches, our approach is robust to dynamically changing environmental conditions (e.g., varying crowd levels, object placement/layout changes); (b) Second, unlike prior work on visual and 3D SLAM, LiLoc is not dependent on a pre-built static map of the environment and instead works by utilizing dynamically updated point clouds captured from both infrastructural-mounted LiDARs and LiDARs equipped on individual mobile IoT devices. To achieve fine-grained, …

Are You Cloud-Certified? Preparing Computing Undergraduates For Cloud Certification With Experiential Learning, Eng Lieh Ouh, Benjamin Gan

Research Collection School Of Computing and Information Systems

Cloud Computing skills have been increasing in demand. Many software engineers are learning these skills and taking cloud certification examinations to be job competitive. Preparing undergraduates to be cloud-certified remains challenging as cloud computing is a relatively new topic in the computing curriculum, and many of these certifications require working experience. In this paper, we report our experiences designing a course with experiential learning to prepare our computing undergraduates to take the cloud certification. We adopt a university project-based experiential learning framework to engage industry partners who provide project requirements for students to develop cloud solutions and an experiential risk …

Compositional Prompt Tuning With Motion Cues For Open-Vocabulary Video Relation Detection, Kaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao, Qianru Sun

Research Collection School Of Computing and Information Systems

Prompt tuning with large-scale pretrained vision-language models empowers open-vocabulary prediction trained on limited base categories, e.g., object classification and detection. In this paper, we propose compositional prompt tuning with motion cues: an extended prompt tuning paradigm for compositional predictions of video data. In particular, we present Relation Prompt (RePro) for Open-vocabulary Video Visual Relation Detection (Open-VidVRD), where conventional prompt tuning is easily biased to certain subject-object combinations and motion patterns. To this end, RePro addresses the two technical challenges of Open-VidVRD: 1) the prompt tokens should respect the two different semantic roles of subject and object, and 2) the tuning …

Link Prediction On Latent Heterogeneous Graphs, Trung Kien Nguyen, Zemin Liu, Yuan Fang

Research Collection School Of Computing and Information Systems

On graph data, the multitude of node or edge types gives rise to heterogeneous information networks (HINs). To preserve the heterogeneous semantics on HINs, the rich node/edge types become a cornerstone of HIN representation learning. However, in real-world scenarios, type information is often noisy, missing or inaccessible. Assuming no type information is given, we define a so-called latent heterogeneous graph (LHG), which carries latent heterogeneous semantics as the node/edge types cannot be observed. In this paper, we study the challenging and unexplored problem of link prediction on an LHG. As existing approaches depend heavily on type-based information, they are suboptimal …

Graphprompt: Unifying Pre-Training And Downstream Tasks For Graph Neural Networks, Zemin Liu, Xingtong Yu, Yuan Fang, Xinming Zhang

Research Collection School Of Computing and Information Systems

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune"and "pre-train, prompt"paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on …

Contrabert: Enhancing Code Pre-Trained Models Via Contrastive Learning, Shangqing Liu, Bozhi Wu, Xiaofei Xie, Guozhu Meng, Yang. Liu

Research Collection School Of Computing and Information Systems

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple downstream tasks such as clone detection, code search and code translation. However, it is also observed that these state-of-the-art pre-trained models are susceptible to adversarial attacks. The performance of these pre-trained models drops significantly with simple perturbations such as renaming variable names. This weakness may be inherited by their downstream models and thereby amplified at an unprecedented scale. To this end, we propose an approach namely ContraBERT that aims …

Widget Detection-Based Testing For Industrial Mobile Games, Xiongfei Wu, Jiaming Ye, Ke Chen, Xiaofei Xie, Ruochen Huang, Lei Ma, Jianjun Zhao

Research Collection School Of Computing and Information Systems

The fast advances in mobile hardware and widespread smartphone usage have fueled the growth of global mobile gaming in the past decade. As a result, the need for quality assurance of mobile gaming has become increasingly pressing. While general-purpose testing methods have been developed for mobile applications, they become struggling when being applied to mobile games due to the unique characteristics of mobile games, such as dynamic loading and stunning visual effects. There comes a growing industrial demand for automated testing techniques with high compatibility (compatible with various resolutions, and platforms) and non-intrusive characteristics (without packaging external modules into the …