Tech Services on the Web: MALLET-MAchine Learning for LanguagE Toolkit; http://mallet.cs.umass.edu/

Falk, Patricia K.

doi:10.1080/07317131.2014.943038

Cited by 5 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We intentionally chose a simple but highly scalable NLP approach because the main context of application was RWE studies that require rapid-cycle analytics and risk prediction models to provide clinical decision support at the point of care. 5,7,8 Future research could assess the trade-off between complexity and scalability when using more sophisticated unsupervised NLP tools, such as named entity recognition (clinical and contextual information extraction and encoding), [33][34][35][36] distributional semantics models, [37][38][39] and word embeddings. 40,41 A thorough comparison of these alternative approaches is beyond our scope.…”

Section: Discussionmentioning

confidence: 99%

Scalable Feature Engineering from Electronic Free Text Notes to Supplement Confounding Adjustment of Claims‐Based Pharmacoepidemiologic Studies

Wyss

Plasek

Zhou

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Natural language processing (NLP) tools turn free-text notes (FTNs) from electronic health records (EHRs) into data features that can supplement confounding adjustment in pharmacoepidemiologic studies. However, current applications are difficult to scale. We used unsupervised NLP to generate high-dimensional feature spaces from FTNs to improve prediction of drug exposure and outcomes compared with claims-based analyses. We linked Medicare claims with EHR data to generate three cohort studies comparing different classes of medications on the risk of various clinical outcomes. We used "bag-of-words" to generate features for the top 20,000 most prevalent terms from FTNs. We compared machine learning (ML) prediction algorithms using different sets of candidate predictors: Set1 (39 researcherspecified variables), Set2 (Set1 + ML-selected claims codes), and Set3 (Set1 + ML-selected NLP-generated features), vs. Set4 (Set1 + 2 + 3). When modeling treatment choice, we observed a consistent pattern across the examples: ML models utilizing Set4 performed best followed by Set2, Set3, then Set1. When modeling the outcome risk, there was little to no improvement beyond models based on Set1. Supplementing claims data with NLP-generated features from free text notes improved prediction of prescribing choices but had little or no improvement on clinical risk prediction. These findings have implications for strategies to improve confounding using EHR data in pharmacoepidemiologic studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Scalable Feature Engineering from Electronic Free Text Notes to Supplement Confounding Adjustment of Claims‐Based Pharmacoepidemiologic Studies

Wyss

Plasek

Zhou

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

show abstract

“…It uses several machine learning algorithms to allow the automatic classification of text documents into classes. MALLET is a general-purpose document classifier, and its ability to classify manually generated spam emails has been demonstrated [51].…”

Section: Methodsmentioning

confidence: 99%

Analysis and Prevention of AI-Based Phishing Email Attacks

Eze,

Shamir

2024

Electronics

View full text Add to dashboard Cite

Phishing email attacks are among the most common and most harmful cybersecurity attacks. With the emergence of generative AI, phishing attacks can be based on emails generated automatically, making it more difficult to detect them. That is, instead of a single email format sent to a large number of recipients, generative AI can be used to send each potential victim a different email, making it more difficult for cybersecurity systems to identify the scam email before it reaches the recipient. Here, we describe a corpus of AI-generated phishing emails. We also use different machine learning tools to test the ability of automatic text analysis to identify AI-generated phishing emails. The results are encouraging, and show that machine learning tools can identify an AI-generated phishing email with high accuracy compared to regular emails or human-generated scam emails. By applying descriptive analytics, the specific differences between AI-generated emails and manually crafted scam emails are profiled and show that AI-generated emails are different in their style from human-generated phishing email scams. Therefore, automatic identification tools can be used as a warning for the user. The paper also describes the corpus of AI-generated phishing emails that are made open to the public and can be used for consequent studies. While the ability of machine learning to detect AI-generated phishing emails is encouraging, AI-generated phishing emails are different from regular phishing emails, and therefore, it is important to train machine learning systems also with AI-generated emails in order to repel future phishing attacks that are powered by generative AI.

show abstract

“…We used the software package MALLET version 2.0.8 (McCallum, 2002) to conduct topic modeling. This system uses probabilistic algorithms to computationally identify topics from large text corpora.…”

Section: Methodsmentioning

confidence: 99%

Make Tweets Great Again: Who Are Opinion Leaders, and What Did They Tweet About Donald Trump?

Alexandre

Yoo

Murthy

2021

Social Science Computer Review

View full text Add to dashboard Cite

Twitter gained new levels of political prominence with Donald J. Trump’s use of the platform. Although previous work has been done studying the content of Trump’s tweets, there remains a dearth of research exploring who opinion leaders were in the early days of his presidency and what they were tweeting about. Therefore, this study retroactively investigates opinion leaders on Twitter during Trump’s 1st month in office and explores what those influencers tweeted about. We uniquely used a historical data set of 3 million tweets that contained the word “trump” and used Latent Dirichlet Allocation, a probabilistic algorithmic model, to extract topics from both general Twitter users and opinion leaders. Opinion leaders were identified by measuring eigenvector centrality and removing users with fewer than 10,000 followers. The top 1% users with the highest score in eigencentrality ( N = 303) were sampled, and their attributes were manually coded. We found that most Twitter-based opinion leaders are either media outlets/journalists with a left-center bias or social bots. Immigration was found to be a key topic during our study period. Our empirical evidence underscores the influence of bots on social media even after the 2016 U.S. presidential election, providing further context to ongoing revelations and disclosures about influence operations during that election. Furthermore, our results provide evidence of the continued relevance of established, “traditional” media sources on Twitter as opinion leaders.

show abstract

Tech Services on the Web: MALLET-MAchine Learning for LanguagE Toolkit; http://mallet.cs.umass.edu/

Cited by 5 publications

References 0 publications

Scalable Feature Engineering from Electronic Free Text Notes to Supplement Confounding Adjustment of Claims‐Based Pharmacoepidemiologic Studies

Scalable Feature Engineering from Electronic Free Text Notes to Supplement Confounding Adjustment of Claims‐Based Pharmacoepidemiologic Studies

Analysis and Prevention of AI-Based Phishing Email Attacks

Make Tweets Great Again: Who Are Opinion Leaders, and What Did They Tweet About Donald Trump?

Contact Info

Product

Resources

About