arXiv subjects

Arjun Mukherjee

Publications and source records attributed to Arjun Mukherjee.

33 records · Page 2Linked to original sources

arXiv2020

Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution

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 sentiment regression. The framework works by exploiting the correlations between sentence-level embedding features and variations of document-level aspect rating scores. We demonstrate several variations of our framework on top of CNN and RNN based models. Experiments on a hotel review dataset and a beer review dataset have shown SAAM can improve sentiment analysis performance over corresponding base models. Moreover, because of the way our framework intuitively combines sentence-level scores into document-level scores, it is able to provide a deeper insight into data (e.g., semi-supervised sentence aspect labeling). Hence, we end the paper with a detailed analysis that shows the potential of our models for other applications such as sentiment snippet extraction.

cs.CL↗

arXiv2020

Cannot Predict Comment Volume of a News Article before (a few) Users Read It

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 (several tens of comments) or a spontaneous fervent user engagement (thousands of comments). In this paper, we study the problem of predicting the total number of user comments a news article will receive. Our main insight is that the early dynamics of user comments contribute the most to an accurate prediction, while news article specific factors have surprisingly little influence. This appears to be an interesting and understudied phenomenon: collective social behavior at a news outlet shapes user response and may even downplay the content of an article. We compile and analyze a large number of features, both old and novel from literature. The features span a broad spectrum of facets including news article and comment contents, temporal dynamics, sentiment/linguistic features, and user behaviors. We show that the early arrival rate of comments is the best indicator of the eventual number of comments. We conduct an in-depth analysis of this feature across several dimensions, such as news outlets and news article categories. We show that the relationship between the early rate and the final number of comments as well as the prediction accuracy vary considerably across news outlets and news article categories (e.g., politics, sports, or health).

cs.IR↗

arXiv2020

Towards Demystifying Dimensions of Source Code Embeddings

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-dimensional vectors computed by training deep neural networks on a large volume of programs. Although successful, there is little known about the contents of these vectors and their characteristics. In this paper, we present our preliminary results towards better understanding the contents of code2vec neural source code embeddings. In particular, in a small case study, we use the code2vec embeddings to create binary SVM classifiers and compare their performance with the handcrafted features. Our results suggest that the handcrafted features can perform very close to the highly-dimensional code2vec embeddings, and the information gains are more evenly distributed in the code2vec embeddings compared to the handcrafted features. We also find that the code2vec embeddings are more resilient to the removal of dimensions with low information gains than the handcrafted features. We hope our results serve a stepping stone toward principled analysis and evaluation of these code representations.

cs.LG↗

arXiv2020

Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models

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, and Title-driven approaches for summarization. We describe a new framework, NewsSumm, that includes many existing and new approaches for summarization including ILP and title-driven approaches. NewsSumm's flexibility allows to combine different algorithms and sentence scoring schemes seamlessly. Our results combining sentence scoring with ILP and normalization are in contrast to previous work on this topic, showing the importance of a broader search for optimal parameters. We also show that the new title-driven reduction idea leads to improvement in performance for both unsupervised and supervised approaches considered.

cs.IR↗

arXiv2020

Birds of a Feather Flock Together: Satirical News Detection via Language Model Differentiation

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. We found that in satirical news, the lexical and pragmatical attributes of the context are the key factors in amusing the readers. In this work, we propose a method that differentiates the satirical news and true news. It takes advantage of satirical writing evidence by leveraging the difference between the prediction loss of two language models, one trained on true news and the other on satirical news, when given a new news article. We compute several statistical metrics of language model prediction loss as features, which are then used to conduct downstream classification. The proposed method is computationally effective because the language models capture the language usage differences between satirical news documents and traditional news documents, and are sensitive when applied to documents outside their domains.

cs.CL↗

arXiv2020

Less is More: Exploiting Social Trust to Increase the Effectiveness of a Deception Attack

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 users' reason about the scams and frauds can help security providers to improve users security hygiene practices. In this work, we study the users' reasoning and the effectiveness of several variables within the context of the company representative fraud. Some of the variables that we study are: 1) the effect of using LinkedIn as a medium for delivering the phishing message instead of using email, 2) the effectiveness of natural language generation techniques in generating phishing emails, and 3) how some simple customizations, e.g., adding sender's contact info to the email, affect participants perception. The results obtained from the within-subject study show that participants are not prepared even for a well-known attack - company representative fraud. Findings include: approximately 65% mean detection rate and insights into how the success rate changes with the facade and correspondent (sender/receiver) information. A significant finding is that a smaller set of well-chosen strategies is better than a large `mess' of strategies. We also find significant differences in how males and females approach the same company representative fraud. Insights from our work could help defenders in developing better strategies to evaluate their defenses and in devising better training strategies.

cs.CR↗

arXiv2020

Stance Prediction for Contemporary Issues: Data and Experiments

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 covering 419 different controversial issues and their related pros and cons collected by procon.org in nonpartisan format. Experimental results show that a shallow recurrent neural network with sentiment or emotion information can reach competitive results compared to fine-tuned BERT with 20x fewer parameters. We also use a simple approach that explains which input phrases contribute to stance detection.

cs.CL↗

arXiv2019

Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network

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 expression within the original sentence context. In this work, we formulate the task as an instance of token-level sequence labeling. When multiple aspects are present in a sentence, detection of opinion phrase boundary becomes difficult and label of each word depend not only upon the surrounding words but also with the concerned aspect. We propose a neural network architecture with bidirectional LSTM (Bi-LSTM) and a novel attention mechanism. Bi-LSTM layer learns the various sequential pattern among the words without requiring any hand-crafted features. The attention mechanism captures the importance of context words on a particular aspect opinion expression when multiple aspects are present in a sentence via location and content based memory. A Conditional Random Field (CRF) model is incorporated in the final layer to explicitly model the dependencies among the output labels. Experimental results on Hotel dataset from Tripadvisor.com showed that our approach outperformed several state-of-the-art baselines.

cs.CL↗

arXiv2018

Interaction of light and semiconductor can generate quantum states required for solid state quantum computing: Entangled, steered and other nonclassical states

Proposals for solid state quantum computing are extremely promising as they can be used to built room temperature quantum computers. If such a quantum computer is ever built it would require in-built sources of nonclassical states required for various quantum information processing tasks. Possibilities of generation of such nonclassical states are investigated here for a physical system composed of a monochromatic light coupled to a two-band semiconductor with direct band gap. The model Hamiltonian includes both photon-exciton and exciton-exciton interactions. Time evolution of the relevant bosonic operators are obtained analytically by using a perturbative technique that provides operator solution for the coupled Heisenberg's equations of motion corresponding to the system Hamiltonian. The bosonic operators are subsequently used to study the possibilities of observing single and two mode squeezing and antibunching after interaction in the relevant modes of light and semiconductor. Further, entanglement between the exciton and photon modes is reported. Finally, the nonclassical effects have been studied numerically for the open quantum system scenario. In this situation, the nonlocal correlations between two modes are shown to violate EPR steering inequality. The observed nonclassical features, induced due to exciton-exciton pair interaction, can be controlled by the phase of input field and the correlations between two modes are shown to enhance due to nonclassicality in the input field.

quant-ph↗

arXiv2018

Experiments with Neural Networks for Small and Large Scale Authorship Verification

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 small and large scale datasets. The underlying small-scale problem has two main challenges: First, the authors of the documents are unknown to us because no previous writing samples are available. Second, the two documents are short (a few hundred to a few thousand words) and may differ considerably in the genre and/or topic. To solve it we propose transformation encoder to transform one document of the pair into the other. This document transformation generates a loss which is used as a recognizable feature to verify if the authors of the pair are identical. For the large scale problem where various authors are engaged and more examples are available with larger length, a parallel recurrent neural network is proposed. It compares the language models of the two documents. We evaluate our methods on various types of datasets including Authorship Identification datasets of PAN competition, Amazon reviews, and machine learning articles. Experiments show that both methods achieve stable and competitive performance compared to the baselines.

cs.CL↗

arXiv2017

Satirical News Detection and Analysis using Attention Mechanism and Linguistic Features

Satirical news is considered to be entertainment, but it is potentially deceptive and harmful. Despite the embedded genre in the article, not everyone can recognize the satirical cues and therefore believe the news as true news. We observe that satirical cues are often reflected in certain paragraphs rather than the whole document. Existing works only consider document-level features to detect the satire, which could be limited. We consider paragraph-level linguistic features to unveil the satire by incorporating neural network and attention mechanism. We investigate the difference between paragraph-level features and document-level features, and analyze them on a large satirical news dataset. The evaluation shows that the proposed model detects satirical news effectively and reveals what features are important at which level.

cs.CL↗

arXiv2017

ENWalk: Learning Network Features for Spam Detection in Twitter

Social medias are increasing their influence with the vast public information leading to their active use for marketing by the companies and organizations. Such marketing promotions are difficult to identify unlike the traditional medias like TV and newspaper. So, it is very much important to identify the promoters in the social media. Although, there are active ongoing researches, existing approaches are far from solving the problem. To identify such imposters, it is very much important to understand their strategies of social circle creation and dynamics of content posting. Are there any specific spammer types? How successful are each types? We analyze these questions in the light of social relationships in Twitter. Our analyses discover two types of spammers and their relationships with the dynamics of content posts. Our results discover novel dynamics of spamming which are intuitive and arguable. We propose ENWalk, a framework to detect the spammers by learning the feature representations of the users in the social media. We learn the feature representations using the random walks biased on the spam dynamics. Experimental results on large-scale twitter network and the corresponding tweets show the effectiveness of our approach that outperforms the existing approaches

cs.LG↗

arXiv2017

Characterizing Product Lifecycle in Online Marketing: Sales, Trust, Revenue, and Competition Modeling

Recent researches have seen an upsurge in the analysis of consumer reviews. Although, several dimensions have been explored, less is known on the temporal dynamics of events that happen over the lifecycle of online products. What are the dominant sales patterns? How are they affected by review count, rating, helpfulness and sentiment? How is trust characterized and what are its effects on sales and revenue? What happens during a market competition? When does a takeover/recovery happen and by what percentage do sales increase on a takeover? This work aims to answer these fundamental research questions based on a sales time-series analysis of reviews of over 1 million products from Amazon.com. We discover novel temporal patterns of sales and interesting correlations of sales with the ratings. We find that trust and helpfulness are important for higher revenue. Based on the analyses, we propose a model to forecast sales that significantly outperforms other baselines. We then explore the phenomena of market competition. Particularly, we characterize different factors that govern survival/death of a product under competition and a model for competition forecast. Experimental results on large-scale reviews demonstrate the effectiveness of the proposed approaches.

cs.SI↗

arXiv2017

Detecting Sockpuppets in Deceptive Opinion Spam

This paper explores the problem of sockpuppet detection in deceptive opinion spam using authorship attribution and verification approaches. Two methods are explored. The first is a feature subsampling scheme that uses the KL-Divergence on stylistic language models of an author to find discriminative features. The second is a transduction scheme, spy induction that leverages the diversity of authors in the unlabeled test set by sending a set of spies (positive samples) from the training set to retrieve hidden samples in the unlabeled test set using nearest and farthest neighbors. Experiments using ground truth sockpuppet data show the effectiveness of the proposed schemes.

cs.CL↗

arXiv2016

Modeling Review Spam Using Temporal Patterns and Co-bursting Behaviors

Online reviews play a crucial role in helping consumers evaluate and compare products and services. However, review hosting sites are often targeted by opinion spamming. In recent years, many such sites have put a great deal of effort in building effective review filtering systems to detect fake reviews and to block malicious accounts. Thus, fraudsters or spammers now turn to compromise, purchase or even raise reputable accounts to write fake reviews. Based on the analysis of a real-life dataset from a review hosting site (dianping.com), we discovered that reviewers' posting rates are bimodal and the transitions between different states can be utilized to differentiate spammers from genuine reviewers. Inspired by these findings, we propose a two-mode Labeled Hidden Markov Model to detect spammers. Experimental results show that our model significantly outperforms supervised learning using linguistic and behavioral features in identifying spammers. Furthermore, we found that when a product has a burst of reviews, many spammers are likely to be actively involved in writing reviews to the product as well as to many other products. We then propose a novel co-bursting network for detecting spammer groups. The co-bursting network enables us to produce more accurate spammer groups than the current state-of-the-art reviewer-product (co-reviewing) network.

cs.SI↗