Availability of affordable image and video capturing devices as well as rapid development of social networking and content sharing websites has led to the creation of new type of content, Social Media. Any system serving the end user’s query search request should not only take the relevant images into consideration but they also need to be divergent for a well-rounded description of a query. As a result, the automated optimization of image retrieval results that are also divergent becomes exceedingly important.



The main focus of this thesis is to use visual description of a landmark by choosing the most diverse pictures that best describe all the details of the queried location from community-contributed datasets. For this, an end-to-end framework has been built, to retrieve relevant results that are also diverse. Different retrieval re-ranking and diversification strategies are evaluated to find a balance between relevance and diversification. Clustering techniques are employed to improve divergence. A unique fusion approach has been adopted to overcome the dilemma of selecting an appropriate clustering technique and the corresponding parameters, given a set of data to be investigated. Extensive experiments have been conducted on the Flickr Div150Cred dataset that has 30 different landmark locations. The results obtained are promising when evaluated on metrics for relevance and diversification.

ASU’s Software Engineering (SER) program adequately prepares students for what happens after they become a developer, but there is no standard for preparing students to secure a job post-graduation in the first place. This project creates and executes a supplemental curriculum to prepare students for the technical interview process. The trial run of the curriculum was received positively by study participants, who experienced an increase in confidence over the duration of the workshop.

The Semantic Web contains large amounts of related information in the form of knowledge graphs such as DBpedia. These knowledge graphs are typically enormous and are not easily accessible for users as they need specialized knowledge in query languages (such as SPARQL) as well as deep familiarity of the ontologies used by these knowledge graphs. So, to make these knowledge graphs more accessible (even for non- experts) several question answering (QA) systems have been developed over the last decade. Due to the complexity of the task, several approaches have been undertaken that include techniques from natural language processing (NLP), information retrieval (IR), machine learning (ML) and the Semantic Web (SW). At a higher level, most question answering systems approach the question answering task as a conversion from the natural language question to its corresponding SPARQL query. These systems then utilize the query to retrieve the desired entities or literals. One approach to solve this problem, that is used by most systems today, is to apply deep syntactic and semantic analysis on the input question to derive the SPARQL query. This has resulted in the evolution of natural language processing pipelines that have common characteristics such as answer type detection, segmentation, phrase matching, part-of-speech-tagging, named entity recognition, named entity disambiguation, syntactic or dependency parsing, semantic role labeling, etc.

This has lead to NLP pipeline architectures that integrate components that solve a specific aspect of the problem and pass on the results to subsequent components for further processing eg: DBpedia Spotlight for named entity recognition, RelMatch for relational mapping, etc. A major drawback in this approach is error propagation that is a common problem in NLP. This can occur due to mistakes early on in the pipeline that can adversely affect successive steps further down the pipeline. Another approach is to use query templates either manually generated or extracted from existing benchmark datasets such as Question Answering over Linked Data (QALD) to generate the SPARQL queries that is basically a set of predefined queries with various slots that need to be filled. This approach potentially shifts the question answering problem into a classification task where the system needs to match the input question to the appropriate template (class label).

This thesis proposes a neural network approach to automatically learn and classify natural language questions into its corresponding template using recursive neural networks. An obvious advantage of using neural networks is the elimination for the need of laborious feature engineering that can be cumbersome and error prone. The input question would be encoded into a vector representation. The model will be trained and evaluated on the LC-QuAD Dataset (Large-scale Complex Question Answering Dataset). The dataset was created explicitly for machine learning based QA approaches for learning complex SPARQL queries. The dataset consists of 5000 questions along with their corresponding SPARQL queries over the DBpedia dataset spanning 5042 entities and 615 predicates. These queries were annotated based on 38 unique templates that the model will attempt to classify. The resulting model will be evaluated against both the LC-QuAD dataset and the Question Answering Over Linked Data (QALD-7) dataset.

The recursive neural network achieves template classification accuracy of 0.828 on the LC-QuAD dataset and an accuracy of 0.618 on the QALD-7 dataset. When the top-2 most likely templates were considered the model achieves an accuracy of 0.945 on the LC-QuAD dataset and 0.786 on the QALD-7 dataset.

After slot filling, the overall system achieves a macro F-score 0.419 on the LC- QuAD dataset and a macro F-score of 0.417 on the QALD-7 dataset.

Since the advent of the internet and even more after social media platforms, the explosive growth of textual data and its availability has made analysis a tedious task. Information extraction systems are available but are generally too specific and often only extract certain kinds of information they deem necessary and extraction worthy. Using data visualization theory and fast, interactive querying methods, leaving out information might not really be necessary. This thesis explores textual data visualization techniques, intuitive querying, and a novel approach to all-purpose textual information extraction to encode large text corpus to improve human understanding of the information present in textual data.

This thesis presents a modified traversal algorithm on dependency parse output of text to extract all subject predicate object pairs from text while ensuring that no information is missed out. To support full scale, all-purpose information extraction from large text corpuses, a data preprocessing pipeline is recommended to be used before the extraction is run. The output format is designed specifically to fit on a node-edge-node model and form the building blocks of a network which makes understanding of the text and querying of information from corpus quick and intuitive. It attempts to reduce reading time and enhancing understanding of the text using interactive graph and timeline.

Academia is not what it used to be. In today’s fast-paced world, requirements

are constantly changing, and adapting to these changes in an academic curriculum

can be challenging. Given a specific aspect of a domain, there can be various levels of

proficiency that can be achieved by the students. Considering the wide array of needs,

diverse groups need customized course curriculum. The need for having an archetype

to design a course focusing on the outcomes paved the way for Outcome-based

Education (OBE). OBE focuses on the outcomes as opposed to the traditional way of

following a process [23]. According to D. Clark, the major reason for the creation of

Bloom’s taxonomy was not only to stimulate and inspire a higher quality of thinking

in academia – incorporating not just the basic fact-learning and application, but also

to evaluate and analyze on the facts and its applications [7]. Instructional Module

Development System (IMODS) is the culmination of both these models – Bloom’s

Taxonomy and OBE. It is an open-source web-based software that has been

developed on the principles of OBE and Bloom’s Taxonomy. It guides an instructor,

step-by-step, through an outcomes-based process as they define the learning

objectives, the content to be covered and develop an instruction and assessment plan.

The tool also provides the user with a repository of techniques based on the choices

made by them regarding the level of learning while defining the objectives. This helps

in maintaining alignment among all the components of the course design. The tool

also generates documentation to support the course design and provide feedback

when the course is lacking in certain aspects.

It is not just enough to come up with a model that theoretically facilitates

effective result-oriented course design. There should be facts, experiments and proof

that any model succeeds in achieving what it aims to achieve. And thus, there are two

research objectives of this thesis: (i) design a feature for course design feedback and

evaluate its effectiveness; (ii) evaluate the usefulness of a tool like IMODS on various

aspects – (a) the effectiveness of the tool in educating instructors on OBE; (b) the

effectiveness of the tool in providing appropriate and efficient pedagogy and

assessment techniques; (c) the effectiveness of the tool in building the learning

objectives; (d) effectiveness of the tool in document generation; (e) Usability of the

tool; (f) the effectiveness of OBE on course design and expected student outcomes.

The thesis presents a detailed algorithm for course design feedback, its pseudocode, a

description and proof of the correctness of the feature, methods used for evaluation

of the tool, experiments for evaluation and analysis of the obtained results.

The functional programming paradigm is able to provide clean and concise solutions to many common programming problems, as well as promote safer, more testable code by encouraging an isolation of state-modifying behavior. Functional programming is finding its way into traditionally object-oriented and imperative languages, most notably with the introduction of Java 8 and in LINQ for C#. However, no functional programming language has achieved widespread adoption, meaning that students without a formal computer science background who learn technology on-demand for personal projects or for business may not come across functional programming in a significant way. Programmers need a reason to spend time learning these concepts to not miss out on the subtle but profound benefits they provide. I propose the use of a video game as an environment in which learning functional programming is the player's goal. In this carefully constructed video game, learning functional programming is the key to progression. Players will be motivated to learn and will be given an immediate chance to test and demonstrate their understanding. The game, named Lambda Starship (stylized as (lambda () starship)), is a 3D first-person video game. It takes place in a spaceship that, due to extreme magnetic interference, has lost all on-board software while leaving the hardware completely intact. The player is tasked to write software using functional programming paradigms to replace the old software and bring the spaceship back to a working state. Throughout the process, the player is guided by an in-game manual and other descriptive resources. The game is implemented in Unity and scripted using C#. The game's educational and entertainment value was evaluated with a study case. 24 undergraduate students at Arizona State University (ASU) played the game and were surveyed detailing their experience. During play, user statistics were recorded automatically, providing a data-driven way to analyze where players struggled with the concepts introduced in the game. Reception was neutral or positive in both the entertainment and educational sides of the game. A few players expressed concerns about the manual in its form factor and engagement value.

Many organizational course design methodologies feature general guidelines for the chronological and time-management aspects of course design development. Proper course structure and instructional strategy pacing has been shown to facilitate student knowledge acquisition of novel material. These course-scheduling details influencing student learning outcomes implies the need for an effective and tightly coupled component of an instructional module. The Instructional Module Development System, or IMODS, seeks to improve STEM, or ‘science, technology, engineering, and math’, education, by equipping educators with a powerful informational tool that helps guide course design by providing information based on contemporary research about pedagogical methodology and assessment practices. This is particularly salient within the higher-education STEM fields because many instructors come from backgrounds that are more technical and most Ph.Ds. in science fields have traditionally not focused on preparing doctoral candidates to teach. This thesis project aims to apply a multidisciplinary approach, blending educational psychology and computer science, to help improve STEM education. By developing an instructional module-scheduling feature for the Web-based IMODS, Instructional Module Development System, system, we can help instructors plan out and organize their course work inside and outside of the classroom, while providing them with relevant helpful research that will help them improve their courses. This article illustrates the iterative design process to gather background research on pacing of workload and learning activities and their influence on student knowledge acquisition, constructively critique and analyze pre-existing information technology (IT) scheduling tools, synthesize graphical user interface, or GUI, mockups based on the background research, and then implement a functional-working prototype using the IMODs framework.

This undergraduate thesis explores the efficacy of developing a translator generator in the Prolog programming language using Lexical Functional Grammars. A bidirectional machine translator between English and Hungarian, developed as a proof-of-concept case study, is discussed and assessed. The benefits and drawbacks of this approach as generalized to Machine Translation systems are also discussed, along with possible areas of future work.

In today's data-driven world, every datum is connected to a large amount of data. Relational databases have been proving itself a pioneer in the field of data storage and manipulation since 1970s. But more recently they have been challenged by NoSQL graph databases in handling data models which have an inherent graphical representation. Graph databases with the ability to store physical relationships between two nodes and native graph processing technique have been doing exceptionally well in graph data storage and management for applications like recommendation engines, biological modeling, network modeling, social media applications, etc.

Instructional Module Development System (IMODS) is a web-based software system that guides STEM instructors through the complex task of curriculum design, ensures tight alignment between various components of a course (i.e., learning objectives, content, assessments), and provides relevant information about research-based pedagogical and assessment strategies. The data model of IMODS is highly connected and has an inherent graphical representation between all its entities with numerous relationships between them. This thesis focuses on developing an algorithm to determine completeness of course design developed using IMODS. As part of this research objective, the study also analyzes the data model for best fit database to run these algorithms. As part of this thesis, two separate applications abstracting the data model of IMODS have been developed - one with Neo4j (graph database) and another with PostgreSQL (relational database). The research objectives of the thesis are as follows: (i) evaluate the performance of Neo4j and PostgreSQL in handling complex queries that will be fired throughout the life cycle of the course design process; (ii) devise an algorithm to determine the completeness of a course design developed using IMODS. This thesis presents the process of creating data model for PostgreSQL and converting it into a graph data model to be abstracted by Neo4j, creating SQL and CYPHER scripts for undertaking experiments on both platforms, testing and elaborate analysis of the results and evaluation of the databases in the context of IMODS.

Ensemble learning methods like bagging, boosting, adaptive boosting, stacking have traditionally shown promising results in improving the predictive accuracy in classification. These techniques have recently been widely used in various domains and applications owing to the improvements in computational efficiency and distributed computing advances. However, with the advent of wide variety of applications of machine learning techniques to class imbalance problems, further focus is needed to evaluate, improve and optimize other performance measures such as sensitivity (true positive rate) and specificity (true negative rate) in classification. This thesis demonstrates a novel approach to evaluate and optimize the performance measures (specifically sensitivity and specificity) using ensemble learning methods for classification that can be especially useful in class imbalanced datasets. In this thesis, ensemble learning methods (specifically bagging and boosting) are used to optimize the performance measures (sensitivity and specificity) on a UC Irvine (UCI) 130 hospital diabetes dataset to predict if a patient will be readmitted to the hospital based on various feature vectors. From the experiments conducted, it can be empirically concluded that, by using ensemble learning methods, although accuracy does improve to some margin, both sensitivity and specificity are optimized significantly and consistently over different cross validation approaches. The implementation and evaluation has been done on a subset of the large UCI 130 hospital diabetes dataset. The performance measures of ensemble learners are compared to the base machine learning classification algorithms such as Naive Bayes, Logistic Regression, k Nearest Neighbor, Decision Trees and Support Vector Machines.