Artificial Intelligence and Robotics Commons^™

Early Detection Of Fake News On Social Media, Yang Liu

Dissertations

The ever-increasing popularity and convenience of social media enable the rapid widespread of fake news, which can cause a series of negative impacts both on individuals and society. Early detection of fake news is essential to minimize its social harm. Existing machine learning approaches are incapable of detecting a fake news story soon after it starts to spread, because they require certain amounts of data to reach decent effectiveness which take time to accumulate. To solve this problem, this research first analyzes and finds that, on social media, the user characteristics of fake news spreaders distribute significantly differently from those …

A Qualitative Representation Of Spatial Scenes In R2 With Regions And Lines, Joshua Lewis

Electronic Theses and Dissertations

Regions and lines are common geographic abstractions for geographic objects. Collections of regions, lines, and other representations of spatial objects form a spatial scene, along with their relations. For instance, the states of Maine and New Hampshire can be represented by a pair of regions and related based on their topological properties. These two states are adjacent (i.e., they meet along their shared boundary), whereas Maine and Florida are not adjacent (i.e., they are disjoint).

A detailed model for qualitatively describing spatial scenes should capture the essential properties of a configuration such that a description of the represented objects …

Information Extraction From Biomedical Text Using Machine Learning, Deepti Garg

Master's Projects

Inadequate drug experimental data and the use of unlicensed drugs may cause adverse drug reactions, especially in pediatric populations. Every year the U.S. Food and Drug Administration approves human prescription drugs for marketing. The labels associated with these drugs include information about clinical trials and drug response in pediatric population. In order for doctors to make an informed decision about the safety and effectiveness of these drugs for children, there is a need to analyze complex and often unstructured drug labels. In this work, first, an exploratory analysis of drug labels using a Natural Language Processing pipeline is performed. Second, …

A Hybrid Approach For Multi-Document Text Summarization, Rashmi Varma

Master's Projects

Text summarization has been a long studied topic in the field of natural language processing. There have been various approaches for both extractive text summarization as well as abstractive text summarization. Summarizing texts for a single document is a methodical task. But summarizing multiple documents poses as a greater challenge. This thesis explores the application of Latent Semantic Analysis, Text-Rank, Lex-Rank and Reduction algorithms for single document text summarization and compares it with the proposed approach of creating a hybrid system combining each of the above algorithms, individually, with Restricted Boltzmann Machines for multi-document text summarization and analyzing how all …

Music Retrieval System Using Query-By-Humming, Parth Patel

Master's Projects

Music Information Retrieval (MIR) is a particular research area of great interest because there are various strategies to retrieve music. To retrieve music, it is important to find a similarity between the input query and the matching music. Several solutions have been proposed that are currently being used in the application domain(s) such as Query- by-Example (QBE) which takes a sample of an audio recording playing in the background and retrieves the result. However, there is no efficient approach to solve this problem in a Query-by-Humming (QBH) application. In a Query-by-Humming application, the aim is to retrieve music that is …

Reputation-Aware Trajectory-Based Data Mining In The Internet Of Things (Iot), Samia Tasnim

FIU Electronic Theses and Dissertations

Internet of Things (IoT) is a critically important technology for the acquisition of spatiotemporally dense data in diverse applications, ranging from environmental monitoring to surveillance systems. Such data helps us improve our transportation systems, monitor our air quality and the spread of diseases, respond to natural disasters, and a bevy of other applications. However, IoT sensor data is error-prone due to a number of reasons: sensors may be deployed in hazardous environments, may deplete their energy resources, have mechanical faults, or maybe become the targets of malicious attacks by adversaries. While previous research has attempted to improve the quality of …

Evaluating Conversation Agent Impact On Student Experience In A Distance Education Course, Grover Walters

USF Tampa Graduate Theses and Dissertations

We explore the efficacy of conversation agents operating as an instructional aid in a distance education course. Two aspects of efficacy are considered—conversation agent impact on student perceptions of the experience, and how different design features of the agent affect student perceptions of engagement. Evaluation of the agent is accomplished by collecting data from 24 undergraduate participants separated into random groups. We conduct two rounds of mixedmethod evaluation. Between the two rounds, a modification to the agent occurs based on the outcome of the first evaluation. Findings include limitations related to phrasing and data persistence features of the design that …

Stylistic Features Usage: Similarities And Differences Using Multiple Social Networks, Kholoud Khalil Aldous, Jisun An, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

User engagement on social networks is essential for news outlets where they often distribute online content. News outlets simultaneously leverage multiple social media platforms to reach their overall audience and to increase marketshare. In this research, we analyze ten common stylistic features indicative of user engagement for news postings on multiple social media platforms. We display the stylistic features usage differences of news posts from various news sources. Results show that there are differences in the usage of stylistic features across social media platforms (Facebook, Instagram, Twitter, and YouTube). Online news outlets can benefit from these findings in building guidelines …

Neural Models For Information Retrieval Without Labeled Data, Hamed Zamani

Doctoral Dissertations

Recent developments of machine learning models, and in particular deep neural networks, have yielded significant improvements on several computer vision, natural language processing, and speech recognition tasks. Progress with information retrieval (IR) tasks has been slower, however, due to the lack of large-scale training data as well as neural network models specifically designed for effective information retrieval. In this dissertation, we address these two issues by introducing task-specific neural network architectures for a set of IR tasks and proposing novel unsupervised or \emph{weakly supervised} solutions for training the models. The proposed learning solutions do not require labeled training data. Instead, …

Response Retrieval In Information-Seeking Conversations, Liu Yang

Doctoral Dissertations

The increasing popularity of mobile Internet has led to several crucial changes in the way that people use search engines compared with traditional Web search on desktops. On one hand, there is limited output bandwidth with the small screen sizes of most mobile devices. Mobile Internet users prefer direct answers on the search engine result page (SERP). On the other hand, voice-based / text-based conversational interfaces are becoming increasing popular as shown in the wide adoption of intelligent assistant services and devices such as Amazon Echo, Microsoft Cortana and Google Assistant around the world. These important changes have triggered several …

Neural Generative Models And Representation Learning For Information Retrieval, Qingyao Ai

Doctoral Dissertations

Information Retrieval (IR) concerns about the structure, analysis, organization, storage, and retrieval of information. Among different retrieval models proposed in the past decades, generative retrieval models, especially those under the statistical probabilistic framework, are one of the most popular techniques that have been widely applied to Information Retrieval problems. While they are famous for their well-grounded theory and good empirical performance in text retrieval, their applications in IR are often limited by their complexity and low extendability in the modeling of high-dimensional information. Recently, advances in deep learning techniques provide new opportunities for representation learning and generative models for information …

Who, Where, And What To Wear?: Extracting Fashion Knowledge From Social Media, Yunshan Ma, Xun Yang, Lizi Liao, Yixin Cao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Fashion knowledge helps people to dress properly and addresses not only physiological needs of users, but also the demands of social activities and conventions. It usually involves three mutually related aspects of: occasion, person and clothing. However, there are few works focusing on extracting such knowledge, which will greatly benefit many downstream applications, such as fashion recommendation. In this paper, we propose a novel method to automatically harvest fashion knowledge from social media. We unify three tasks of occasion, person and clothing discovery from multiple modalities of images, texts and metadata. For person detection and analysis, we use the off-the-shelf …

Automatic Fashion Knowledge Extraction From Social Media, Yunshan Ma, Lizi Liao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Fashion knowledge plays a pivotal role in helping people in their dressing. In this paper, we present a novel system to automatically harvest fashion knowledge from social media. It unifies three tasks of occasion, person and clothing discovery from multiple modalities of images, texts and metadata. A contextualized fashion concept learning model is applied to leverage the rich contextual information for improving the fashion concept learning performance. At the same time, to counter the label noise within training data, we employ a weak label modeling method to further boost the performance. We build a website to demonstrate the quality of …

Weakly-Supervised Deep Anomaly Detection With Pairwise Relation Learning, Guansong Pang, Anton Van Den Hengel, Chuanhua Shen

Research Collection School Of Computing and Information Systems

This paper studies a rarely explored but critical anomaly detection problem: weakly-supervised anomaly detection with limited labeled anomalies and a large unlabeled data set. This problem is very important because it (i) enables anomalyinformed modeling which helps identify anomalies of interests and address the notorious high false positives in unsupervised anomaly detection, and (ii) eliminates the reliance on large-scale and complete labeled anomaly data in fullysupervised settings. However, the problem is especially challenging since we have only limited labeled data for a single class, and moreover, the seen anomalies often cannot cover all types of anomalies (i.e., unseen anomalies). We …

End-To-End Deep Reinforcement Learning For Multi-Agent Collaborative Exploration, Zichen Chen, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Exploring an unknown environment by multiple autonomous robots is a major challenge in robotics domains. As multiple robots are assigned to explore different locations, they may interfere each other making the overall tasks less efficient. In this paper, we present a new model called CNN-based Multi-agent Proximal Policy Optimization (CMAPPO) to multi-agent exploration wherein the agents learn the effective strategy to allocate and explore the environment using a new deep reinforcement learning architecture. The model combines convolutional neural network to process multi-channel visual inputs, curriculum-based learning, and PPO algorithm for motivation based reinforcement learning. Evaluations show that the proposed method …

Multi-Agent Collaborative Exploration Through Graph-Based Deep Reinforcement Learning, Tianze Luo, Budhitama Subagdja, Ah-Hwee Tan, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Autonomous exploration by a single or multiple agents in an unknown environment leads to various applications in automation, such as cleaning, search and rescue, etc. Traditional methods normally take frontier locations and segmented regions of the environment into account to efficiently allocate target locations to different agents to visit. They may employ ad hoc solutions to allocate the task to the agents, but the allocation may not be efficient. In the literature, few studies focused on enhancing the traditional methods by applying machine learning models for agent performance improvement. In this paper, we propose a graph-based deep reinforcement learning approach …

Amazon Alexa + Linked Open Data: Theorizing Concerning Relationships Between (Surveillant) Smart-Home Voice Assistants And Linked Open Data, Michelle Nitto

Publications and Research

No abstract provided.

Foodai: Food Image Recognition Via Deep Learning For Smart Food Logging, Doyen Sahoo, Hao Wang, Ke Shu, Xiongwei Wu, Hung Le, Palakorn Achananuparp, Ee-Peng Lim, Hoi, Steven C. H.

Research Collection School Of Computing and Information Systems

An important aspect of health monitoring is effective logging of food consumption. This can help management of diet-related diseases like obesity, diabetes, and even cardiovascular diseases. Moreover, food logging can help fitness enthusiasts, and people who wanting to achieve a target weight. However, food-logging is cumbersome, and requires not only taking additional effort to note down the food item consumed regularly, but also sufficient knowledge of the food item consumed (which is difficult due to the availability of a wide variety of cuisines). With increasing reliance on smart devices, we exploit the convenience offered through the use of smart phones …

Adapting Bert For Target-Oriented Multimodal Sentiment Classification, Jianfei Yu, Jing Jiang

Research Collection School Of Computing and Information Systems

As an important task in Sentiment Analysis, Target-oriented Sentiment Classification (TSC) aims to identify sentiment polarities over each opinion target in a sentence. However, existing approaches to this task primarily rely on the textual content, but ignoring the other increasingly popular multimodal data sources (e.g., images), which can enhance the robustness of these text-based models. Motivated by this observation and inspired by the recently proposed BERT architecture, we study Target-oriented Multimodal Sentiment Classification (TMSC) and propose a multimodal BERT architecture. To model intra-modality dynamics, we first apply BERT to obtain target-sensitive textual representations. We then borrow the idea from self-attention …

Ezlog: Data Visualization For Logistics, Aldy Gunawan, Benjamin Gan, Jin An Tan, Sheena L.S.L Villanueva, Timothy K.J. Wen

Research Collection School Of Computing and Information Systems

With the increasing availabilityof data in the logistics industry due to the digitalization trend, interest andopportunities for leveraging analytics in supply chain management to makedata-driven decisions is growing rapidly. In this paper, we introduce EzLog, anintegrated visualization prototype platform for supply chain analytics. Thisweb-based platform built by two undergraduate student teams for their capstonecourse can be used for data wrangling and rapid analysis of data from differentbusiness units of a major logistics company. Other functionalities of thesystem include standard processes to perform data analysis such as supervisedextraction, transformation, loading (ETL), data type validation and mapping.Weather, real-time stock market and Twitter …

Probabilistic Models For Identifying And Explaining Controversy, Myungha Jang

Doctoral Dissertations

Navigating controversial topics on the Web encourages social awareness, supports civil discourse, and promotes critical literacy. While search of controversial topics particularly requires users to use their critical literacy skills on the content, educating people to be more critical readers is known to be a complex and long-term process. Therefore, we are in need of search engines that are equipped with techniques to help users to understand controversial topics by identifying them and explaining why they are controversial. A few approaches for identifying controversy have worked reasonably well in practice, but they are narrow in scope and exhibit limited performance. …

One-Class Order Embedding For Dependency Relation Prediction, Meng-Fen Chiang, Ee-Peng Lim, Wang-Chien Lee, Xavier Jayaraj Siddarth Ashok, Philips Kokoh Prasetyo

Research Collection School Of Computing and Information Systems

Learning the dependency relations among entities and the hierarchy formed by these relations by mapping entities into some order embedding space can effectively enable several important applications, including knowledge base completion and prerequisite relations prediction. Nevertheless, it is very challenging to learn a good order embedding due to the existence of partial ordering and missing relations in the observed data. Moreover, most application scenarios do not provide non-trivial negative dependency relation instances. We therefore propose a framework that performs dependency relation prediction by exploring both rich semantic and hierarchical structure information in the data. In particular, we propose several negative …

Self-Supervised Spatio-Temporal Representation Learning For Videos By Predicting Motion And Appearance Statistics, Jiangliu Wang, Jianbo Jiao, Linchao Bao, Shengfeng He, Yunhui Liu, Wei Liu

Research Collection School Of Computing and Information Systems

We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tasks where spatio-temporal features are prevailing. In this paper we propose a novel self-supervised approach to learn spatio-temporal features for video representation. Inspired by the success of two-stream approaches in video classification, we propose to learn visual features by regressing both motion and appearance statistics along spatial and temporal dimensions, given only the input video data. Specifically, we …

Influence Analysis Based On Political Twitter Data, Jace Rose

Master's Projects

Studies of online behavior often consider how users interact online, their posting behaviors, what they are tweeting about, and how likely they are to follow other people. The problem is there is that no deeper study on the people that a user has interacted with and how these other users affect them. This study examines if it is possible to draw similar sentiment from users with whom the target user has interacted with. The data collection process gathers data from Twitter users posting to popular political hashtags, which the highest at the time published were #MAGA and #TRUMP, as well …

Topic Classification Using Hybrid Of Unsupervised And Supervised Learning, Jayant Shelke

Master's Projects

There has been research around the idea of representing words in text as vectors and many models proposed that vary in performance as well as applications. Text processing is used for content recommendation, sentiment analysis, plagiarism detection, content creation, language translation, etc. to name a few. Specifically, we want to look at the problem of topic detection in text content of articles/blogs/summaries. With the humungous amount of text content published each and every minute on the internet, it is imperative that we have very good algorithms and approaches to analyze all the content and be able to classify most of …

Image Retrieval Using Image Captioning, Nivetha Vijayaraju

Master's Projects

The rapid growth in the availability of the Internet and smartphones have resulted in the increase in usage of social media in recent years. This increased usage has thereby resulted in the exponential growth of digital images which are available. Therefore, image retrieval systems play a major role in fetching images relevant to the query provided by the users. These systems should also be able to handle the massive growth of data and take advantage of the emerging technologies, like deep learning and image captioning. This report aims at understanding the purpose of image retrieval and various research held in …

An Ensemble Model For Click Through Rate Prediction, Muthaiah Ramanathan

Master's Projects

Internet has become the most prominent and accessible way to spread the news about an event or to pitch, advertise and sell a product, globally. The success of any advertisement campaign lies in reaching the right class of target audience and eventually convert them as potential customers in the future. Search engines like the Google, Yahoo, Bing are a few of the most used ones by the businesses to market their product. Apart from this, certain websites like the www.alibaba.com that has more traffic also offer services for B2B customers to set their advertisement campaign. The look of the advertisement, …

Sentiment Analysis For Search Engine, Saravana Gunaseelan

Master's Projects

The chief purpose of this study is to detect and eliminate the sentiment bias in a search engine. Sentiment bias means a bias induced in the search results based on the sentiment of the user’s search query. As people increasing depend on search engines for information, it is important to understand the quality of results produced by the search engines. This study does not try to build a search engine but leverage the existing search engines to provide better results to the user. In this study, only the queries that have high sentiment polarity are analyzed and the machine learning …

Predictive Analysis For Cloud Infrastructure Metrics, Paridhi Agrawal

Master's Projects

In a cloud computing environment, enterprises have the flexibility to request resources according to their application demands. This elastic feature of cloud computing makes it an attractive option for enterprises to host their applications on the cloud. Cloud providers usually exploit this elasticity by auto-scaling the application resources for quality assurance. However, there is a setup-time delay that may take minutes between the demand for a new resource and it being prepared for utilization. This causes the static resource provisioning techniques, which request allocation of a new resource only when the application breaches a specific threshold, to be slow and …

Beyond Autonomy: The Self And Life Of Social Agents, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Agents have gained popularity nowadays as virtual assistants and companions of their human users supporting daily activities in many aspects of personal life. Designed to be sociable, an agent engages its user(s) to communicate and even develop friendships. Rather than just as a lifeless toy, it is supposed to be perceived as an individual with its own personality, experiences, and social life. In this paper, we seek to highlight self-hood as another dimension that characterizes an agent. Besides levels of autonomy and reasoning, an agent can be defined based on its capacity to process and reflect on its own self …