Aditya Joshi

ORCID: 0000-0003-2200-9703
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Sentiment Analysis and Opinion Mining
  • Natural Language Processing Techniques
  • Advanced Text Analysis Techniques
  • Text and Document Classification Technologies
  • Spam and Phishing Detection
  • Neural Networks and Applications
  • Misinformation and Its Impacts
  • Data-Driven Disease Surveillance
  • Quantum, superfluid, helium dynamics
  • Mental Health via Writing
  • Atomic and Subatomic Physics Research
  • Hate Speech and Cyberbullying Detection
  • Speech and dialogue systems
  • Text Readability and Simplification
  • Computational Physics and Python Applications
  • Biomedical Text Mining and Ontologies
  • Cold Atom Physics and Bose-Einstein Condensates
  • Authorship Attribution and Profiling
  • Influenza Virus Research Studies
  • Access Control and Trust
  • Machine Learning and Data Classification
  • Advanced Neural Network Applications
  • Computational and Text Analysis Methods
  • Hand Gesture Recognition Systems

UNSW Sydney
2023-2025

Graphic Era University
2020-2024

Manipal University Jaipur
2024

Symbiosis International University
2024

National Institute of Technology Warangal
2023

St. Luke's Hospital
2022

Mount Sinai Hospital
2022

Penn State Milton S. Hershey Medical Center
2022

Bar-Ilan University
2021

University of Helsinki
2021

The research community has increasing interest in autonomous driving research, despite the resource intensity of obtaining representative real world data. Existing self-driving datasets are limited scale and variation environments they capture, even though generalization within between operating regions is crucial to over-all viability technology. In an effort help align community's contributions with real-world problems, we introduce a new large scale, high quality, diverse dataset. Our...

10.1109/cvpr42600.2020.00252 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020-06-01

Aditya Joshi, Vinita Sharma, Pushpak Bhattacharyya. Proceedings of the 53rd Annual Meeting Association for Computational Linguistics and 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 2015.

10.3115/v1/p15-2124 article EN 2015-01-01

This paper makes a simple increment to state-of-the-art in sarcasm detection research. Existing approaches are unable capture subtle forms of context incongruity which lies at the heart sarcasm. We explore if prior work can be enhanced using semantic similarity/discordance between word embeddings. augment embedding-based features four feature sets reported past. also experiment with types observe an improvement detection, irrespective embedding used or original set our augmented. For...

10.18653/v1/d16-1104 article EN Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing 2016-01-01

Automatic sarcasm detection is the task of predicting in text. This a crucial step to sentiment analysis, considering prevalence and challenges sentiment-bearing Beginning with an approach that used speech-based features, has witnessed great interest from analysis community. paper first known compilation past work automatic detection. We observe three milestones research so far: semi-supervised pattern extraction identify implicit sentiment, use hashtag-based supervision, context beyond...

10.48550/arxiv.1602.03426 preprint EN other-oa arXiv (Cornell University) 2016-01-01

Sarcasm understanding may require information beyond the text itself, as in case of 'I absolutely love this restaurant!' which be sarcastic, depending on contextual situation.We present first quantitative evidence to show that historical tweets by an author can provide additional context for sarcasm detection.Our detection approach uses two components: a contrast-based predictor (that identifies if there is sentiment contrast within target tweet), and tweet-based expressed towards entity...

10.18653/v1/w15-2905 article EN cc-by 2015-01-01

We present Queer in AI as a case study for community-led participatory design AI. examine how and intersectional tenets started shaped this community's programs over the years. discuss different challenges that emerged process, look at ways organization has fallen short of operationalizing principles, then assess organization's impact. provides important lessons insights practitioners theorists methods broadly through its rejection hierarchy favor decentralization, success building aid by...

10.1145/3593013.3594134 article EN 2022 ACM Conference on Fairness, Accountability, and Transparency 2023-06-12

Sentiment analysis (SA) using code-mixed data from social media has several applications in opinion mining ranging customer satisfaction to campaign multilingual societies. Advances this area are impeded by the lack of a suitable annotated dataset. We introduce Hindi-English (Hi-En) dataset for sentiment and perform empirical comparing suitability performance various state-of-the-art SA methods media. In paper, we learning sub-word level representations LSTM (Subword-LSTM) architecture...

10.48550/arxiv.1611.00472 preprint EN cc-by arXiv (Cornell University) 2016-01-01

This paper is a novel study that views sarcasm detection in dialogue as sequence labeling task, where made up of utterances.We create manuallylabeled dataset from TV series 'Friends' annotated with sarcasm.Our goal to predict each utterance, using sequential nature scene.We show performance gain compared classification-based approaches.Our experiments are based on three sets features, one derived information our dataset, the other two past works.Two algorithms (SVM-HMM and SEARN) outperform...

10.18653/v1/k16-1015 article EN cc-by 2016-01-01

This paper reports an increment to the state-of-the-art in hate speech detection for English-Hindi code-mixed tweets. We compare three typical deep learning models using domain-specific embeddings. On experimenting with a benchmark dataset of tweets, we observe that embeddings results improved representation target groups, and F-score.

10.48550/arxiv.1811.05145 preprint EN other-oa arXiv (Cornell University) 2018-01-01

Level of Trust can determine which source information is reliable and with whom we should share or from accept information. There are several applications for measuring trust in Online Social Networks (OSNs), including social spammer detection, fake news retweet behaviour detection recommender systems. prediction the process predicting a new relation between two users who not currently connected. In trust, relations among need to be predicted. This faces many challenges, such as sparsity...

10.1109/access.2020.3009445 article EN cc-by IEEE Access 2020-01-01

Background: Melbourne, Australia, witnessed a thunderstorm asthma outbreak on 21 November 2016, resulting in over 8,000 hospital admissions by 6 p.m . This is typical acute disease event. Because the time to respond short for events, an algorithm based between events has shown promise. Shorter consecutive incidents of disease, more likely outbreak. Social media posts such as tweets can be used input monitoring algorithm. However, due large volume tweets, number alerts may produced. We refer...

10.1097/ede.0000000000001133 article EN Epidemiology 2019-10-25

Harnessing data from social media to monitor health events is a promising avenue for public surveillance. A key step the detection of reports disease (referred as 'health mention classification') amongst tweets that words. Prior work shows figurative usage words may prove be challenging classification. Since experience associated with negative sentiment, we present method utilises sentiment information improve Specifically, our classifier classification combines pre-trained contextual word...

10.1145/3366423.3380198 article EN 2020-04-20

The effort required for a human annotator to detect sentiment is not uniform all texts, irrespective of his/her expertise. We aim predict score that quantifies this effort, using linguistic properties the text. Our proposed metric called Sentiment Annotation Complexity (SAC). As training data, since any direct judgment complexity by fraught with subjectivity, we rely on cognitive evidence from eye-tracking. sentences in our dataset are labeled SAC scores derived eye-fixation duration. Using...

10.3115/v1/p14-2007 article EN 2014-01-01

First reported in March 2014, an Ebola epidemic impacted West Africa, most notably Liberia, Guinea and Sierra Leone. We demonstrate the value of social media for automated surveillance infectious diseases such as Africa epidemic. experiment with two variations existing architecture: first aggregates tweets related to different symptoms together, while second considers about each symptom separately then set alerts generated by architecture. Using a dataset posted from affected region 2011 we...

10.1371/journal.pone.0230322 article EN cc-by PLoS ONE 2020-03-17
Coming Soon ...