Digital Commons Network^™

Textual Emotion Detection Approaches: A Survey, Mahinda Mahmoud Samy Zidan, Ibrahim Elhenawy, Ahmed R. Abas, Mahmoud Othman

Future Computing and Informatics Journal

Over the past decades, social media attracted individuals to express their feelings on any topic or item, resulting in an incremental growth in the size of created data. These feelings and unstructured data paved the path for business organizations to gather information and build statistical analysis. Various machine learning and natural language processing-based approaches are used for sentiment and emotion analysis. Moreover, deep learning-based approaches recently gained popularity due to their remarkable performance in text analysis. This paper provides a comprehensive overview of the prominent machine learning models applied in emotion analysis. It explores various emotion analysis taxonomies, in addition …

Knowledge-Infused Learning, Manas Gaur

Theses and Dissertations

In DARPA’s view of the three waves of AI, the first wave of AI, symbolic AI, focused on explicit knowledge. The second and current wave of AI is termed statistical AI. Deep learning techniques have been able to exploit large amounts of data and massive computational power to improve human levels of performance in narrowly defined tasks. Separately, knowledge graphs have emerged as a powerful tool to capture and exploit a variety of explicit knowledge to make algorithms better apprehend the content and enable the next generation of data processing, such as semantic search. After initial hesitancy about the scalability …

Querai – A Smart Quiz Generator, Elton Da Silva, Fernando Aires Da Silva, Kim Jang Womg, Tai Teei Ho

ICT

QUERAI is a website powered by an Artificial Intelligence Question & Answer quiz generator model aiming to enhance students' learning experience and improve teachers' qualitative work by giving them more time to deal with other activities such as assignment correction, general grading, and class preparation.

A Novel Hybrid Algorithm For Morphological Analysis: Artificial Neural-Net-Xmor, Ayla Kayabaş, Ahmet Ercan Topcu, Özkan Kiliç

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, we present a novel algorithm that combines a rule-based approach and an artificial neural network-based approach in morphological analysis. The usage of hybrid models including both techniques is evaluated for performance improvements. The proposed hybrid algorithm is based on the idea of the dynamic generation of an artificial neural network according to two-level phonological rules. In this study, the combination of linguistic parsing, a neural network-based error correction model, and statistical filtering is utilized to increase the coverage of pure morphological analysis. We experimented hybrid algorithm applying rule-based and long short-term memory-based (LSTM-based) techniques, and the results …

Automatic Keyword Assignment System For Medical Research Articles Using Nearest-Neighbor Searches, Fati̇h Di̇lmaç, Adi̇l Alpkoçak

Turkish Journal of Electrical Engineering and Computer Sciences

Assigning accurate keywords to research articles is increasingly important concern. Keywords should be selected meticulously to describe the article well since keywords play an important role in matching readers with research articles in order to reach a bigger audience. So, improper selection of keywords may result in less attraction to readers which results in degradation in its audience. Hence, we designed and developed an automatic keyword assignment system (AKAS) for research articles based on k-nearest neighbor (k-NN) and threshold-nearest neighbor (t-NN) accompanied with information retrieval systems (IRS), which is a corpus-based method by utilizing IRS using the Medline dataset in …

Learning Term Weights By Overfitting Pairwise Ranking Loss, Ömer Şahi̇n, İlyas Çi̇çekli̇, Gönenç Ercan

Turkish Journal of Electrical Engineering and Computer Sciences

A search engine strikes a balance between effectiveness and efficiency to retrieve the best documents in a scalable way. Recent deep learning-based ranker methods are proving to be effective and improving the state-of-the-art in relevancy metrics. However, as opposed to index-based retrieval methods, neural rankers like bidirectional encoder representations from transformers (BERT) do not scale to large datasets. In this article, we propose a query term weighting method that can be used with a standard inverted index without modifying it. Query term weights are learned using relevant and irrelevant document pairs for each query, using a pairwise ranking loss. The …

Automated Question Generation And Question Answering From Turkish Texts, Fati̇h Çağatay Akyön, Ali̇ Devri̇m Eki̇n Çavuşoğlu, Cemi̇l Cengi̇z, Si̇nan Onur Altinuç, Alpteki̇n Temi̇zel

Turkish Journal of Electrical Engineering and Computer Sciences

While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience and resources. Automatic question generation (QG) techniques can be utilized to satisfy the need for a continuous supply of new questions by streamlining their generation. However, compared to automatic question answering (QA), QG is a more challenging task. In this work, we fine-tune a multilingual T5 (mT5) transformer in a multitask setting for QA, QG and answer extraction tasks using Turkish QA datasets. To the best of our knowledge, this is the first academic work …

Learning To Ask Critical Questions For Assisting Product Search, Zixuan Li, Lizi Liao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Product search plays an essential role in eCommerce. It was treated as a special type of information retrieval problem. Most existing works make use of historical data to improve the search performance, which do not take the opportunity to ask for user’s current interest directly. Some session-aware methods take the user’s clicks within the session as implicit feedback, but it is still just a guess on user’s preference. To address this problem, recent conversational or question-based search models interact with users directly for understanding the user’s interest explicitly. However, most users do not have a clear picture on what to …

Order Constraints In Optimal Transport, Fabian Lim, Laura Wynter, Shiau Hong Lim

Research Collection School Of Computing and Information Systems

Optimal transport is a framework for comparing measures whereby a cost is incurred for transporting one measure to another. Recent works have aimed to improve optimal transport plans through the introduction of various forms of structure. We introduce novel order constraints into the optimal transport formulation to allow for the incorporation of structure. We define an efficient method for obtaining explainable solutions to the new formulation that scales far better than standard approaches. The theoretical properties of the method are provided. We demonstrate experimentally that order constraints improve explainability using the e-SNLI (Stanford Natural Language Inference) dataset that includes human-annotated …

Harnessing Confidence For Report Aggregation In Crowdsourcing Environments, Hadeel Alhosaini, Xianzhi Wang, Lina Yao, Zhong Yang, Farookh Hussain, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Crowdsourcing is an effective means of accomplishing human intelligence tasks by leveraging the collective wisdom of crowds. Given reports of various accuracy degrees from workers, it is important to make wise use of these reports to derive accurate task results. Intuitively, a task result derived from a sufficient number of reports bears lower uncertainty, and higher uncertainty otherwise. Existing report aggregation research, however, has largely neglected the above uncertainty issue. In this regard, we propose a novel report aggregation framework that defines and incorporates a new confidence measure to quantify the uncertainty associated with tasks and workers, thereby enhancing result …

Computer-Aided Response-To-Intervention For Reading Comprehension Based On Recommender System, Ming-Chi Liu, Wei-Yang Lin, Chia-Ling Tsai

Publications and Research

In 2019, New York State Education Department announced 54.6% of all students in grades 3 to 8 not meeting the standard of reading proficiency. Motivated by the need for a more efficient intervention model, we propose a recommender system to leverage the technology in machine learning to recommend suitable reading materials for effective intervention. The recommendation is based on the student's prior reading comprehension assessments and also assessments of other students at the same grade level using collaborative filtering. No other prior academic or demographic information of students is available. Two main challenges are lack of explicit ratings of reading …

Transmorph: A Transformer Based Morphological Disambiguator For Turkish, Hi̇lal Özer, Emi̇n Erkan Korkmaz

Turkish Journal of Electrical Engineering and Computer Sciences

The agglutinative nature of the Turkish language has a complex morphological structure, and there are generally more than one parse for a given word. Before further processing, morphological disambiguation is required to determine the correct morphological analysis of a word. Morphological disambiguation is one of the first and crucial steps in natural language processing since its success determines later analyses. In our proposed morphological disambiguation method, we used a transformer-based sequence-to-sequence neural network architecture. Transformers are commonly used in various NLP tasks, and they produce state-of-the-art results in machine translation. However, to the best of our knowledge, transformer-based encoder-decoders have …

Docee: A Large-Scale And Fine-Grained Benchmark For Document-Level Event Extraction, Meihan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

Research Collection School Of Computing and Information Systems

Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentencelevel event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major barrier to promote documentlevel event extraction has been the lack of large-scale and practical training and evaluation datasets. In this paper, we present DocEE, a new document-level event extraction dataset including 27,000+ events, 180,000+ arguments. We highlight three features: largescale manual annotations, fine-grained argument types and application-oriented settings. Experiments show that there is still a big …

Early Rumor Detection Using Neural Hawkes Process With A New Benchmark Dataset, Fengzhu Zeng, Wei Gao

Research Collection School Of Computing and Information Systems

Little attention has been paid on EArly Rumor Detection (EARD), and EARD performance was evaluated inappropriately on a few datasets where the actual early-stage information is largely missing. To reverse such situation, we construct BEARD, a new Benchmark dataset for EARD, based on claims from fact-checking websites by trying to gather as many early relevant posts as possible. We also propose HEARD, a novel model based on neural Hawkes process for EARD, which can guide a generic rumor detection model to make timely, accurate and stable predictions. Experiments show that HEARD achieves effective EARD performance on two commonly used general …

A Weakly Supervised Propagation Model For Rumor Verification And Stance Detection With Multiple Instance Learning, Ruichao Yang, Jing Ma, Hongzhan Lin, Wei Gao

Research Collection School Of Computing and Information Systems

The diffusion of rumors on social media generally follows a propagation tree structure, which provides valuable clues on how an original message is transmitted and responded by users over time. Recent studies reveal that rumor verification and stance detection are two relevant tasks that can jointly enhance each other despite their differences. For example, rumors can be debunked by cross-checking the stances conveyed by their relevant posts, and stances are also conditioned on the nature of the rumor. However, stance detection typically requires a large training set of labeled stances at post level, which are rare and costly to annotate. …

Dynamic Topic Models For Temporal Document Networks, Ce Zhang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Dynamic topic models explore the time evolution of topics in temporally accumulative corpora. While existing topic models focus on the dynamics of individual documents, we propose two neural topic models aimed at learning unified topic distributions that incorporate both document dynamics and network structure. For the first model, by adding a time dimension, we propose Time-Aware Optimal Transport, which measures the probability of a link between two differently timestamped documents using their semantic distance. Since the gradually evolving topological structure of network may also influence the establishment of a new link, for the second model, we further design a Temporal …

Declaration-Based Prompt Tuning For Visual Question Answering, Yuhang Liu, Wei Wei, Feida Zhu, Feida Zhu

Research Collection School Of Computing and Information Systems

In recent years, the pre-training-then-fine-tuning paradigm has yielded immense success on a wide spectrum of cross-modal tasks, such as visual question answering (VQA), in which a visual-language (VL) model is first optimized via self-supervised task objectives, e.g., masked language modeling (MLM) and image-text matching (ITM), and then fine-tuned to adapt to downstream task (e.g., VQA) via a brand-new objective function, e.g., answer prediction. However, the inconsistency of the objective forms not only severely limits the generalization of pre-trained VL models to downstream tasks, but also requires a large amount of labeled data for fine-tuning. To alleviate the problem, we propose …

What Makes The Story Forward?: Inferring Commonsense Explanations As Prompts For Future Event Generation, Li Lin, Yixin Cao, Lifu Huang, Shu Ang Li, Xuming Hu, Lijie Wen, Jianmin Wang

Research Collection School Of Computing and Information Systems

Prediction over event sequences is critical for many real-world applications in Information Retrieval and Natural Language Processing. Future Event Generation (FEG) is a challenging task in event sequence prediction because it requires not only fluent text generation but also commonsense reasoning to maintain the logical coherence of the entire event story. In this paper, we propose a novel explainable FEG framework, Coep. It highlights and integrates two types of event knowledge, sequential knowledge of direct event-event relations and inferential knowledge that reflects the intermediate character psychology between events, such as intents, causes, reactions, which intrinsically pushes the story forward. To …

Q2r: A Query-To-Resolution System For Natural-Language Queries, Shiau Hong Lim, Laura Wynter

Research Collection School Of Computing and Information Systems

We present a system for document retrieval that combines direct classification with standard content-based retrieval approaches to significantly improve the relevance of the retrieved documents. Our system exploits the availability of an imperfect but sizable amount of labeled data from past queries. For domains such as technical support, the proposed approach enhances the system’s ability to retrieve documents that are otherwise ranked very low based on content alone. The system is easy to implement and can make use of existing text ranking methods, augmenting them through the novel Q2R orchestration framework. Q2R has been extensively tested and is in use …

Classification Of Twitter Vaping Discourse Using Bertweet: Comparative Deep Learning Study, William Baker, Jason B. Colditz, Page D. Dobbs, Huy Mai, Shyam Visweswaran, Justin Zhan, Brian A. Primack

Computer Science and Computer Engineering Faculty Publications and Presentations

Background:

Twitter provides a valuable platform for the surveillance and monitoring of public health topics; however, manually categorizing large quantities of Twitter data is labor intensive and presents barriers to identify major trends and sentiments. Additionally, while machine and deep learning approaches have been proposed with high accuracy, they require large, annotated data sets. Public pretrained deep learning classification models, such as BERTweet, produce higher-quality models while using smaller annotated training sets.

Objective:

This study aims to derive and evaluate a pretrained deep learning model based on BERTweet that can identify tweets relevant to vaping, tweets (related to vaping) of …

A Concept For Weighting Sentiment Phrase Using Deterministic Solution Of Algebraic Equations, Maryam Jalali, Morteza Zahedi, Abdolali Basiri

Turkish Journal of Electrical Engineering and Computer Sciences

Many text mining methods have used statistical information as text and language-independent procedures that are not deterministic. On the other hand, grammatical structure-based methods are limited to use in a certain language and text. We aim to suggest an algorithmic algebraic equation in a deterministic and nonprobabilistic way while maintaining the advantage of language independence. We propose a mathematical approach that transforms text and labels into a set of dumb equations. By solving the equations, each word is assigned a weight that can reflect the semantic information of that word, then we use the proposed algorithm to build a novel …

Generating Ad Creatives Using Deep Learning For Search Advertising, Kevser Nur Çoğalmiş, Ahmet Bulut

Turkish Journal of Electrical Engineering and Computer Sciences

We generated advertisement creatives programmatically using deep neural networks. A landing page contains relevant text data, which can be used for generating advertisement creatives, i.e. ads. We treated the ad generation task as a text summarization problem and built a sequence to sequence model. In order to assess the validity of our approach, we conducted experiments on four datasets. Our empirical results showed that our model generated relevant ads on a template-based dataset with moderate hyperparameters. Training the model with more content increased the performance of the model, which we attributed to rigorous hyperparameter tune-up. The choice of word embedding …

Adversarial Activity Detection And Prediction Using Behavioral Biometrics, Amin Fallahi

Dissertations - ALL

Behavioral biometrics can be used in different security applications like authentication, identification, etc. One of the trending applications is predicting future activities of people and guessing whether they will engage in malicious activities in the future. In this research, we study the possibility of predicting future activities and propose novel methods for near-future activity prediction.

First, we study gait signals captured using smartphone accelerometer sensor and build a model to predict a future gait signal. Activity recognition using body movements captured from mobile phone sensors has been a major point of interest in recent research. Data that is being continuously …

Interdisciplinary Communication By Plausible Analogies: The Case Of Buddhism And Artificial Intelligence, Michael Cooper

USF Tampa Graduate Theses and Dissertations

Communicating interdisciplinary information is difficult, even when two fields are ostensibly discussing the same topic. In this work, I’ll discuss the capacity for analogical reasoning to provide a framework for developing novel judgments utilizing similarities in separate domains. I argue that analogies are best modeled after Paul Bartha’s By Parallel Reasoning, and that they can be used to create a Toulmin-style warrant that expresses a generalization. I argue that these comparisons provide insights into interdisciplinary research. In order to demonstrate this concept, I will demonstrate that fruitful comparisons can be made between Buddhism and Artificial Intelligence research.

Allure: A Multi-Modal Guided Environment For Helping Children Learn To Solve A Rubik's Cube With Automatic Solving And Interactive Explanations, Kausik Lakkaraju, Thahimum Hassan, Vedant Khandelwal, Prathamjeet Singh, Cassidy Bradley, Ronak Shah, Forest Agostinelli, Biplav Srivastava, Dezhi Wu

Faculty Publications

Modern artificial intelligence (AI) methods have been used to solve problems that many humans struggle to solve. This opens up new opportunities for knowledge discovery and education. We demonstrate ALLURE, a collaborative educational AI system for learning to solve the Rubik's cube that is designed to help students improve their problem solving skills. ALLURE can both find its own strategies for solving the Rubik's cube and explain those strategies to humans. In the future, ALLURE will also be able to collaborate with humans by building on user-provided strategies for solving the Rubik's cube and as well as generalize to other …

Explainable And Cooperative Autonomy Across Networks Of Distributed Systems, Peter Joseph Jorgensen

USF Tampa Graduate Theses and Dissertations

Large networks of complex systems-of-systems are commonplace and evermore present in both mundane and extraordinary facets of human existence. From the exponential growth of connectivity via the internet and other information networks, to the miniaturization of computers and sensors, to cross-domain sensor and communication networks, these networks of distributed systems-of-systems (NDSS) present incredible benefits and challenges. Autonomy is perhaps the most important and most difficult to achieve enabling technology for efficient performance of the NDSS. Giving each individual agent in a network the ability to manage its internal state in dynamic operating environments and in pursuit of multiple complex and …

Determining American Sign Language Joint Trajectory Similarity Using Dynamic Time Warping (Dtw), Rohith Mandavilli

Computer Science Senior Theses

As American Sign Language (ASL), the language used by Deaf/Hard of Hearing (D/HH) Americans has grown in popularity in recent years, an unprecedented number of schools and organizations now offer ASL classes. Many hold misconceptions about ASL, assuming it is easily learned; however due to its rich, complex grammatical construction, it’s not mastered easily beyond a basic level. Therefore, it becomes ever more important to improve upon existing techniques to teach ASL. The Dartmouth Applied Learning Initiative (DALI) at Dartmouth college in coordination with the Robotics and Reality Lab developed an application on the Oculus Quest that helps D/HH individuals …

An Introduction To Artificial Intelligence, Carlos R. Arias

SPU Works

This chapter explores the evolution of artificial intelligence, starting with the first ideas of Alan Turing, going through the promises of its inception, and landing in our current state, when AI invokes a sense of power and awe. Next, the chapter will provide a summary of different technologies related to AI and machine learning, such as deep neural networks, to help the reader distinguish different terminologies. The chapter will end with a discussion of some potential tendencies concerning how AI may be used or evolve in the near future, and some questions about the technology in the long term.

Towards A Computational Model Of Narrative On Social Media, Anne Bailey

Dartmouth College Undergraduate Theses

This thesis describes a variety of approaches to developing a computational model of narrative on social media. Our goal is to use such a narrative model to identify efforts to manipulate public opinion on social media platforms like Twitter. We present a model in which narratives in a collection of tweets are represented as a graph. Elements from each tweet that are relevant to potential narratives are made into nodes in the graph; for this thesis, we populate graph nodes with tweets’ authors, hashtags, named entities (people, locations, organizations, etc.,), and moral foundations (central moral values framing the discussion). Two …

Legislative Language For Success, Sanjana Gundala

Master's Theses

Legislative committee meetings are an integral part of the lawmaking process for local and state bills. The testimony presented during these meetings is a large factor in the outcome of the proposed bill. This research uses Natural Language Processing and Machine Learning techniques to analyze testimonies from California Legislative committee meetings from 2015-2016 in order to identify what aspects of a testimony makes it successful. A testimony is considered successful if the alignment of the testimony matches the bill outcome (alignment is "For" and the bill passes or alignment is "Against" and the bill fails). The process of finding what …