Arjun Mukherjee
YOU?
Author Swipe
View article: Beyond Easy Wins: A Text Hardness-Aware Benchmark for LLM-generated Text Detection
Beyond Easy Wins: A Text Hardness-Aware Benchmark for LLM-generated Text Detection Open
We present a novel evaluation paradigm for AI text detectors that prioritizes real-world and equitable assessment. Current approaches predominantly report conventional metrics like AUROC, overlooking that even modest false positive rates c…
View article: ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination
ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination Open
While large language models (LLMs) exhibit significant utility across various domains, they simultaneously are susceptible to exploitation for unethical purposes, including academic misconduct and dissemination of misinformation. Consequen…
View article: Seeing Through AI's Lens: Enhancing Human Skepticism Towards LLM-Generated Fake News
Seeing Through AI's Lens: Enhancing Human Skepticism Towards LLM-Generated Fake News Open
LLMs offer valuable capabilities, yet they can be utilized by malicious users to disseminate deceptive information and generate fake news. The growing prevalence of LLMs poses difficulties in crafting detection approaches that remain effec…
View article: The Looming Threat of Fake and LLM-generated LinkedIn Profiles
The Looming Threat of Fake and LLM-generated LinkedIn Profiles Open
In this paper, we present a novel method for detecting fake and Large\nLanguage Model (LLM)-generated profiles in the LinkedIn Online Social Network\nimmediately upon registration and before establishing connections. Early fake\nprofile id…
View article: Tackling the Myriads of Collusion Scams on YouTube Comments of Cryptocurrency Videos
Tackling the Myriads of Collusion Scams on YouTube Comments of Cryptocurrency Videos Open
Despite repeated measures, YouTube's comment section has been a fertile ground for scammers.With the growth of the cryptocurrency market and obscurity around it, a new form of scam, namely "Collusion Scam" has emerged as a dominant force w…
View article: Exploring Deceptive Domain Transfer Strategies: Mitigating the Differences among Deceptive Domains
Exploring Deceptive Domain Transfer Strategies: Mitigating the Differences among Deceptive Domains Open
Deceptive text poses a significant threat to users, resulting in widespread misinformation and disorder.While researchers have created numerous cutting-edge techniques for detecting deception in domain-specific settings, whether there is a…
View article: Improving Phishing Detection Via Psychological Trait Scoring
Improving Phishing Detection Via Psychological Trait Scoring Open
Phishing emails exhibit some unique psychological traits which are not present in legitimate emails. From empirical analysis and previous research, we find three psychological traits most dominant in Phishing emails - A Sense of Urgency, I…
View article: What Yelp Fake Review Filter Might Be Doing?
What Yelp Fake Review Filter Might Be Doing? Open
Online reviews have become a valuable resource for decision making. However, its usefulness brings forth a curse ‒ deceptive opinion spam. In recent years, fake review detection has attracted significant attention. However, most review sit…
View article: Analyzing and Detecting Opinion Spam on a Large-scale Dataset via Temporal and Spatial Patterns
Analyzing and Detecting Opinion Spam on a Large-scale Dataset via Temporal and Spatial Patterns Open
Although opinion spam (or fake review) detection has attracted significant research attention in recent years, the problem is far from solved. One key reason is that there is no large-scale ground truth labeled dataset available for model …
View article: Exploiting Burstiness in Reviews for Review Spammer Detection
Exploiting Burstiness in Reviews for Review Spammer Detection Open
Online product reviews have become an important source of user opinions. Due to profit or fame, imposters have been writing deceptive or fake reviews to promote and/or to demote some target products or services. Such imposters are called r…
View article: Opinion Prediction with User Fingerprinting
Opinion Prediction with User Fingerprinting Open
Opinion prediction is an emerging research area with diverse real-world applications, such as market research and situational awareness. We identify two lines of approaches to the problem of opinion prediction. One uses topic-based sentime…
View article: Cannot Predict Comment Volume of a News Article before (a few) Users Read It
Cannot Predict Comment Volume of a News Article before (a few) Users Read It Open
Many news outlets allow users to contribute comments on topics about daily world events. News articles are the seeds that spring users' interest to contribute content, i.e., comments. An article may attract an apathetic user engagement (se…
View article: Claim Verification using a Multi-GAN based Model
Claim Verification using a Multi-GAN based Model Open
This article describes research on claim verification carried out using a multiple GAN-based model. The proposed model consists of three pairs of generators and discriminators. The generator and discriminator pairs are responsible for gene…
View article: Improving Authorship Verification using Linguistic Divergence
Improving Authorship Verification using Linguistic Divergence Open
We propose an unsupervised solution to the Authorship Verification task that utilizes pre-trained deep language models to compute a new metric called DV-Distance. The proposed metric is a measure of the difference between the two authors c…
View article: Improving Evidence Retrieval with Claim-Evidence Entailment
Improving Evidence Retrieval with Claim-Evidence Entailment Open
Claim verification is challenging because it requires first to find textual evidence and then apply claim-evidence entailment to verify a claim.Previous works evaluate the entailment step based on the retrieved evidence, whereas we hypothe…
View article: On the Usefulness of Personality Traits in Opinion-oriented Tasks
On the Usefulness of Personality Traits in Opinion-oriented Tasks Open
We use a deep bidirectional transformer to extract the Myers-Briggs personality type from user-generated data in a multi-label and multiclass classification setting.Our dataset is large and made up of three available personality datasets o…
View article: Claim Verification using a Multi-GAN based Model
Claim Verification using a Multi-GAN based Model Open
This article describes research on claim verification carried out using a multiple GAN-based model.The proposed model consists of three pairs of generators and discriminators.The generator and discriminator pairs are responsible for genera…
View article: Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution
Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution Open
In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM). SAAM works on top of traditional neural networks and is designed to address the problem of multi-aspect sentiment classification and sentime…
View article: Towards demystifying dimensions of source code embeddings
Towards demystifying dimensions of source code embeddings Open
Source code representations are key in applying machine learning techniques for processing and analyzing programs. A popular approach in representing source code is neural source code embeddings that represents programs with high-dimension…
View article: Cannot Predict Comment Volume of a News Article before (a few) Users Read It
Cannot Predict Comment Volume of a News Article before (a few) Users Read It Open
Many news outlets allow users to contribute comments on topics about daily world events. News articles are the seeds that spring users' interest to contribute content, i.e., comments. An article may attract an apathetic user engagement (se…
View article: Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models
Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models Open
In this paper, we revisit the challenging problem of unsupervised single-document summarization and study the following aspects: Integer linear programming (ILP) based algorithms, Parameterized normalization of term and sentence scores, an…
View article: Experiments in Extractive Summarization: Integer Linear Programming,\n Term/Sentence Scoring, and Title-driven Models
Experiments in Extractive Summarization: Integer Linear Programming,\n Term/Sentence Scoring, and Title-driven Models Open
In this paper, we revisit the challenging problem of unsupervised\nsingle-document summarization and study the following aspects: Integer linear\nprogramming (ILP) based algorithms, Parameterized normalization of term and\nsentence scores,…
View article: Birds of a Feather Flock Together: Satirical News Detection via Language Model Differentiation
Birds of a Feather Flock Together: Satirical News Detection via Language Model Differentiation Open
Satirical news is regularly shared in modern social media because it is entertaining with smartly embedded humor. However, it can be harmful to society because it can sometimes be mistaken as factual news, due to its deceptive character. W…
View article: Less is More: Exploiting Social Trust to Increase the Effectiveness of a Deception Attack
Less is More: Exploiting Social Trust to Increase the Effectiveness of a Deception Attack Open
Cyber attacks such as phishing, IRS scams, etc., still are successful in fooling Internet users. Users are the last line of defense against these attacks since attackers seem to always find a way to bypass security systems. Understanding u…
View article: Stance Prediction for Contemporary Issues: Data and Experiments
Stance Prediction for Contemporary Issues: Data and Experiments Open
We investigate whether pre-trained bidirectional transformers with sentiment and emotion information improve stance detection in long discussions of contemporary issues. As a part of this work, we create a novel stance detection dataset co…
View article: Predicting Personal Opinion on Future Events with Fingerprints
Predicting Personal Opinion on Future Events with Fingerprints Open
Predicting users' opinions in their response to social events has important real-world applications, many of which political and social impacts. Existing approaches derive a population's opinion on a going event from large scores of user g…
View article: Robust Authorship Verification with Transfer Learning
Robust Authorship Verification with Transfer Learning Open
We address the problem of open-set authorship verification, a classification task that consists of attributing texts of unknown authorship to a given author when the testing set may differ significantly with the training set in terms of do…
View article: Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network
Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network Open
Opinion phrase extraction is one of the key tasks in fine-grained sentiment analysis. While opinion expressions could be generic subjective expressions, aspect specific opinion expressions contain both the aspect as well as the opinion exp…
View article: Experiments with Neural Networks for Small and Large Scale Authorship Verification
Experiments with Neural Networks for Small and Large Scale Authorship Verification Open
We propose two models for a special case of authorship verification problem. The task is to investigate whether the two documents of a given pair are written by the same author. We consider the authorship verification problem for both smal…