Digital Commons Network^™

Learning Cross-Modal Embeddings With Adversarial Networks For Cooking Recipes And Food Images, Hao Wang, Doyen Sahoo, Chenghao Liu, Ee-Peng Lim, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Food computing is playing an increasingly important role in human daily life, and has found tremendous applications in guiding human behavior towards smart food consumption and healthy lifestyle. An important task under the food-computing umbrella is retrieval, which is particularly helpful for health related applications, where we are interested in retrieving important information about food (e.g., ingredients, nutrition, etc.). In this paper, we investigate an open research task of cross-modal retrieval between cooking recipes and food images, and propose a novel framework Adversarial Cross-Modal Embedding (ACME) to resolve the cross-modal retrieval task in food domains. Specifically, the goal is to …

A Comparative Study Of Russian Trolls Using Several Machine Learning Models On Twitter Data, Kannan Neten Dharan Kannan Neten Dharan

Theses

Ever since Russian trolls have been brought into light, their interference in the 2016 US Presidential elections has been monitored and studied thoroughly. These Russian trolls have fake accounts registered on several major social media sites to influence public opinions. Our work involves trying to discover patterns in these tweets and classifying them by using different machine learning approaches such as Support Vector Machines, Word2vec and neural network models, and then creating a benchmark to compare all the different models. Two machine learning models are developed for this purpose. The first one is used to classify any given specific tweet …

What To Do When Privacy Is Gone, James Brusseau

Computer Ethics - Philosophical Enquiry (CEPE) Proceedings

Today’s ethics of privacy is largely dedicated to defending personal information from big data technologies. This essay goes in the other direction. It considers the struggle to be lost, and explores two strategies for living after privacy is gone. First, total exposure embraces privacy’s decline, and then contributes to the process with transparency. All personal information is shared without reservation. The resulting ethics is explored through a big data version of Robert Nozick’s Experience Machine thought experiment. Second, transient existence responds to privacy’s loss by ceaselessly generating new personal identities, which translates into constantly producing temporarily unviolated private information. The …

Difference Between Algorithmic Processing And The Process Of Lifeworld (Lebenswelt), Domenico Schneider

Computer Ethics - Philosophical Enquiry (CEPE) Proceedings

The following article compares the temporality of the life-world with the digital processing. The temporality of the life-world is determined to be stretched and spontaneous. The temporality of the digital is given by discrete step-by-step points of time. Most ethical issues can be traced back to a mismatch of these two ways of processing. This creates a foundation for the ethics of the digital processing. Methodologically, phenomenological considerations are merged with media-philosophical considerations in the article.

Legal And Technical Issues For Text And Data Mining In Greece, Maria Kanellopoulou - Botti, Marinos Papadopoulos, Christos Zampakolas, Paraskevi Ganatsiou

Computer Ethics - Philosophical Enquiry (CEPE) Proceedings

Web harvesting and archiving pertains to the processes of collecting from the web and archiving of works that reside on the Web. Web harvesting and archiving is one of the most attractive applications for libraries which plan ahead for their future operation. When works retrieved from the Web are turned into archived and documented material to be found in a library, the amount of works that can be found in said library can be far greater than the number of works harvested from the Web. The proposed participation in the 2019 CEPE Conference aims at presenting certain issues related to …

Classifying Challenging Behaviors In Autism Spectrum Disorder With Neural Document Embeddings, Abigail Atchison

Computational and Data Sciences (MS) Theses

The understanding and treatment of challenging behaviors in individuals with Autism Spectrum Disorder is paramount to enabling the success of behavioral therapy; an essential step in this process being the labeling of challenging behaviors demonstrated in therapy sessions. These manifestations differ across individuals and within individuals over time and thus, the appropriate classification of a challenging behavior when considering purely qualitative factors can be unclear. In this thesis we seek to add quantitative depth to this otherwise qualitative task of challenging behavior classification. We do so through the application of natural language processing techniques to behavioral descriptions extracted from the …

Music Mood Classification Using Convolutional Neural Networks, Revanth Akella

Master's Projects

Grouping music into moods is useful as music is migrating from to online streaming services as it can help in recommendations. To establish the connection between music and mood we develop an end-to-end, open source approach for mood classification using lyrics. We develop a pipeline for tag extraction, lyric extraction, and establishing classification models for classifying music into moods. We investigate techniques to classify music into moods using lyrics and audio features. Using various natural language processing methods with machine learning and deep learning we perform a comparative study across different classification and mood models. The results infer that features …

An Industry Driven Genre Classification Application Using Natural Language Processing, Sharan Duggirala

Master's Projects

With the advent of digitized music, many online streaming companies such as Spotify have capitalized on a listener’s need for a common stream platform. An essential component of such a platform is the recommender systems that suggest to the constituent user base, related tracks, albums and artists. In order to sustain such a recommender system, labeling data to indicate which genre it belongs to is essential. Most recent academic publications that deal with music genre classification focus on the use of deep neural networks developed and applied within the music genre classification domain. This thesis attempts to use some of …

Sql Injection Detection Using Machine Learning, Sonali Mishra

Master's Projects

Sharing information over the Internet over multiple platforms and web-applications has become a quite common phenomenon in the recent times. The web-based applications that accept critical information from users store this information in databases. These applications and the databases connected to them are susceptible to all kinds of information security threats due to being accessible through the Internet. The threats include attacks such as Cross Side Scripting (CSS), Denial of Service Attack (DoS0, and Structured Query Language (SQL) Injection attacks. SQL Injection attacks fall under the top ten vulnerabilities when we talk about web-based applications. Through this kind of attack, …

Glovenor - Global Vectors For Node Representations, Shishir Kulkarni

Master's Projects

A graph is a very powerful abstract data type that can be used to model entities (nodes) and relationships (edges). Many real world networks like biological, computer and friendship networks can be represented as graphs. Graphs can be mined to extract interesting patterns and interactions between the participating entities. Recently, various Artificial Intelligence (AI) and Machine Learning (ML) techniques are used for this purpose. In order to do that, the nodes of a graph have to be represented as low dimensional feature vectors. Node embedding is the process of generating a �-dimensional feature vector corresponding to each node of a …

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 …

Chatbots With Personality Using Deep Learning, Susmit Gaikwad

Master's Projects

Natural Language Processing (NLP) requires the computational modelling of the complex relationships of the syntax and semantics of a language. While traditional machine learning methods are used to solve NLP problems, they cannot imitate the human ability for language comprehension. With the growth in deep learning, these complexities within NLP are easier to model, and be used to build many computer applications. A particular example of this is a chatbot, where a human user has a conversation with a computer program, that generates responses based on the user’s input. In this project, we study the methods used in building chatbots, …

Next Level: A Course Recommender System Based On Career Interests, Shehba Shahab

Master's Projects

Skills-based hiring is a talent management approach that empowers employers to align recruitment around business results, rather than around credentials and title. It starts with employers identifying the particular skills required for a role, and then screening and evaluating candidates’ competencies against those requirements. With the recent rise in employers adopting skills-based hiring practices, it has become integral for students to take courses that improve their marketability and support their long-term career success. A 2017 survey of over 32,000 students at 43 randomly selected institutions found that only 34% of students believe they will graduate with the skills and knowledge …

Detection Of Hate Speech In Videos Using Machine Learning, Unnathi Bhandary

Master's Projects

With the progression of the internet and social media, people are given multiple platforms to share their thoughts and opinions about various subject matters freely. However, this freedom of speech is misused to direct hate towards individuals or group of people due to their race, religion, gender etc. The rise of hate speech has led to conflicts and cases of cyber bullying, causing many organizations to look for optimal solutions to solve this problem.

Developments in the field of machine learning and deep learning have piqued the interest of researchers, leading them to research and implement solutions to solve the …

Assessing Bias Removal From Word Embeddings, Clare Arrington

Departmental Honors & Graduate Capstone Projects

As machine learning becomes more influential in everyday life, we must begin addressing potential shortcomings. A current problem area is word embeddings, frameworks that transform words into numbers, allowing the algorithmic analysis of language. Without a method for filtering implicit human bias from the documents used to create these embeddings, they contain and propagate stereotypes. Previous work has shown that one commonly used and distributed word embedding model trained on articles from Google News contained prejudice between gender and occupation (Bolukbasi 2016). While unsurprising, the use of biased data in machine learning models only serves to amplify the problem. Although …

Twitter And Disasters: A Social Resilience Fingerprint, Benjamin A. Rachunok, Jackson B. Bennett, Roshanak Nateghi

Purdue University Libraries Open Access Publishing Fund

Understanding the resilience of a community facing a crisis event is critical to improving its adaptive capacity. Community resilience has been conceptualized as a function of the resilience of components of a community such as ecological, infrastructure, economic, and social systems, etc. In this paper, we introduce the concept of a “resilience fingerprint” and propose a multi-dimensional method for analyzing components of community resilience by leveraging existing definitions of community resilience with data from the social network Twitter. Twitter data from 14 events are analyzed and their resulting resilience fingerprints computed. We compare the fingerprints between events and show that …

Using Data Science To Detect Fake News, Eliza Shoemaker

Senior Honors Projects, 2010-2019

The purpose of this thesis is to assist in automating the detection of Fake News by identifying which features are more useful for different classifiers. The effectiveness of different extracted features for Fake News detection are going to be examined. When classifying text with machine learning algorithms features have to be extracted from the articles for the classifiers to be trained on. In this thesis, several different features are extracted: word counts, ngram counts, term frequency-inverse document frequency, sentiment analysis, lemmatization, and named entity recognition to train the classifiers. Two classifiers are used, a Random Forest classifier and a Naïve …

Leveraging Reviews To Improve User Experience, Anthony Schams, Iram Bakhtiar, Cristina Stanley

SMU Data Science Review

In this paper, we will explore and present a method of finding characteristics of a restaurant using its reviews through machine learning algorithms. We begin by building models to predict the ratings of individual reviews using text and categorical features. This is to examine the efficacy of the algorithms to the task. Both XGBoost and logistic regression will be examined. With these models, our goal is then to identify key phrases in reviews that are correlated with positive and negative experience. Our analysis makes use of review data publicly made available by Yelp. Key bigrams extracted were non-specific to the …

Leveraging Natural Language Processing Applications And Microblogging Platform For Increased Transparency In Crisis Areas, Ernesto Carrera-Ruvalcaba, Johnson Ekedum, Austin Hancock, Ben Brock

SMU Data Science Review

Through microblogging applications, such as Twitter, people actively document their lives even in times of natural disasters such as hurricanes and earthquakes. While first responders and crisis-teams are able to help people who call 911, or arrive at a designated shelter, there are vast amounts of information being exchanged online via Twitter that provide real-time, location-based alerts that are going unnoticed. To effectively use this information, the Tweets must be verified for authenticity and categorized to ensure that the proper authorities can be alerted. In this paper, we create a Crisis Message Corpus from geotagged Tweets occurring during 7 hurricanes …

Tidying And Analysis Of The 2014 Texas English Ii End-Of-Course Exam, David Churchman, Abigail Morton Garland

SMU Data Science Review

The state of Texas requires all public high school students to take End of Course (EOC) exams. The results of these exams are made nominally public, but in a shape and format that precludes ready analysis. To the extent possible, principles of tidy data will be applied to clean and analyze the publicly released data file for the 2014 English II EOC exam, providing insights into the EOC program and a case for better public data from the Texas Education Administration (TEA).

A Hybrid Model To Detect Fake News, Indhumathi Gurunathan

Computer Science Graduate Projects and Theses

The wide availability of user-contributed content in the online social media facilitates aggregation of people around common interests, worldviews, and narratives. But over the years, internet being the source of information also becomes the source of misinformation. As people are generally awash in information, they can sometimes have difficulty discerning misinformation propagated on web platforms from truthful information. They may also lean heavily on information providers or social media platforms to curate information even though such providers do not commonly validate sources. In this project, we primarily focus was on political news and propose a hybrid model to detect misleading …

Twitter Bot Detection In The Context Of The 2018 Us Senate Elections, Wes Kendrick

Dartmouth College Undergraduate Theses

A growing percentage of public political communication takes place on social media sites such as Twitter, and not all of it is posted by humans. If citizens are to have the final say online, we must be able to detect and weed out bot accounts. The objective of this thesis is threefold: 1) expand the pool of Twitter election data available for analysis, 2) evaluate the bot detection performance of humans on a ground-truth dataset, and 3) learn what features humans associate with accounts that they believe to be bots. In this thesis, we build a large database of over …

Worcester Chamber Of Commerce: Recruiting Minority Business Owners, Ryan Dimaria, Alexander Hull, Xikun Lu, Haopeng Wang, Jiacheng Hou, Danning Zhao

School of Professional Studies

Our capstone project was to help the Worcester Regional Chamber of Commerce identify how to re-frame their marketing so it would be appealing to immigrant and minority owned businesses. Based on interviews and external research, our group was able to create a tangible and resourceful data set that provided justified recommendations and ideas on how the Chamber could make adjustments to their marketing plan to attract more businesses of this particular demographic in the city of Worcester. By implementing these recommendations, we believe the Chamber has the opportunity to create a more diverse group of Chamber members, add value to …

Frameannotator - A Web-Based Frame Semantic Annotation Tool, Sarbajit Roy

Computer Science and Engineering Theses - Archive

News headlines around the world are alarming. They aim to trigger emotional responses from the consumer. In an era where news and social media posts spread so quickly, it is often difficult to distinguish between what is real and what is false. Human fact-checking fails to cope with the growth of such unprecedented information, thus increasing the demand and various steps of automatic fact-checking to judge the veracity of claims. An automatic fact-checking system is a statistical model that can help to detect misinformation. The current state-of-the-art frame semantic parsers suffer from lack of a large annotated data-set and there …

Ultra-Context: Maximizing The Context For Better Image Caption Generation, Ankit Khare

Computer Science and Engineering Theses - Archive

Several combinations of visual and semantic attention have been geared towards developing better image captioning architectures. In this work we introduce a novel combination of word-level semantic context with image feature-level visual context, which provides a more holistic overall context for image caption generation. This approach does not require training any explicit network structure, using any external resource for training semantic attributes, or supervision during any training step. The proposed architecture addresses the significance of learning to find context at three levels to achieve a better trade-off as well as a balance between the two lines of attentiveness (word-level and …

The Legacies Of Apollo 11, Gregory A. Dilisi, Greg Brown

2019 Faculty Bibliography

No abstract provided.

Smart Home Audio Assistant, Xipeng Wang

All Computer Science and Engineering Research

This report introduces an audio processing algorithm. It provides a way to access smart devices using audio. Although there are many audio assistants already on the market, most of them will not be able to control the smart devices. Therefore, this new system presented in this report will provide a way to analysis the customer’s questions. Then the algorithm will be able to query smart device information, modify the schedule or provide the reason for some arrangement.

Commonsense Knowledge In Sentiment Analysis Of Ordinance Reactions For Smart Governance, Manish Puri

Theses, Dissertations and Culminating Projects

Smart Governance is an emerging research area which has attracted scientific as well as policy interests, and aims to improve collaboration between government and citizens, as well as other stakeholders. Our project aims to enable lawmakers to incorporate data driven decision making in enacting ordinances. Our first objective is to create a mechanism for mapping ordinances (local laws) and tweets to Smart City Characteristics (SCC). The use of SCC has allowed us to create a mapping between a huge number of ordinances and tweets, and the use of Commonsense Knowledge (CSK) has allowed us to utilize human judgment in mapping. …

Neural Multimodal Belief Tracker With Adaptive Attention For Dialogue Systems, Zheng Zhang, Lizi Liao, Minlie Huang, Xiaoyan Zhu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Multimodal dialogue systems are attracting increasing attention with a more natural and informative way for human-computer interaction. As one of its core components, the belief tracker estimates the user's goal at each step of the dialogue and provides a direct way to validate the ability of dialogue understanding. However, existing studies on belief trackers are largely limited to textual modality, which cannot be easily extended to capture the rich semantics in multimodal systems such as those with product images. For example, in fashion domain, the visual appearance of clothes play a crucial role in understanding the user's intention. In this …

Processing Narratives By Means Of Action Languages, Craig Olson

Computer Science Theses, Dissertations, and Student Creative Activity

In this work we design a narrative understanding system Text2ALM that can be used in Question Answering domains. System Text2ALM utilizes an action language 𝒜ℒℳ to perform inferences on complex interactions of events described in narratives. The methodology that Text2ALM follows in its implementation was originally outlined by Yuliya Lierler, Daniela Inclezan, and Michael Gelfond in 2017 via a manual process, and this work serves as a proof of concept in a large-scale environment. Our system automates the conversion of a narrative to an 𝒜ℒℳ model containing facts about the narrative. We make use of the VerbNet lexicon that we …