• Publications
  • Influence
SentiPers: A Sentiment Analysis Corpus for Persian
TLDR
This paper outlines the entire process of developing a manually annotated sentiment corpus, SentiPers, which covers formal and informal written contemporary Persian and is a unique sentiment corpus with such a rich annotation in three different levels including document-level, sentence- level, and entity/aspect-level for Persian.
LexiPers: An ontology based sentiment lexicon for Persian
TLDR
The process of generating a general purpose sentiment lexicon for Persian using the K-nearest neighbors and nearest centroid methods for classification and a new graph-based method is introduced for seed selection and expansion based on an ontology.
ParsiNLU: A Suite of Language Understanding Challenges for Persian
TLDR
This work introduces ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks—reading comprehension, textual entailment, and so on, and presents the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compares them with human performance.
A Multi-Modal Method for Satire Detection using Textual and Visual Cues
TLDR
This work creates a new dataset consisting of images and headlines of regular and satirical news for the task of satire detection, and proposes a multi-modal approach based on state-of-the-art visiolinguistic model ViLBERT.
Content analysis of Persian/Farsi Tweets during COVID-19 pandemic in Iran using NLP
TLDR
This study analyzed the topics discussed among users of Twitter to gauge and track the response to the pandemic and how it evolved over time, and identified the top 25 topics among which living experience under home quarantine emerged as a major talking point.
Identifying Nuances in Fake News vs. Satire: Using Semantic and Linguistic Cues
TLDR
This work addresses the challenge of automatically classifying fake news versus satire with a machine learning method using semantic representation, with a state-of-the-art contextual language model, and with linguistic features based on textual coherence metrics.
Predicting Directionality in Causal Relations in Text
TLDR
This work test the performance of two bidirectional transformer-based language models, BERT and SpanBERT, on predicting directionality in causal pairs in the textual content and introduces CREST, a framework for unifying a collection of scattered datasets of causal relations.
Does Causal Coherence Predict Online Spread of Social Media?
TLDR
Test the hypothesis that causal and semantic coherence are associated with online sharing of misinformative social media content using Coh-Metrix – a widely-used set of psycholinguistic measures to support Fuzzy-Trace Theory’s predictions regarding the role of causally- and semantically-coherent content and motivate better measures of these key constructs.
Automatically Identifying Political Ads on Facebook: Towards Understanding of Manipulation via User Targeting
TLDR
This work studies the political ads dataset collected by ProPublica using a network of volunteers in the period before the 2018 US midterm elections, and addresses the challenge of automatically classifying between political and non-political ads, and investigates whether the user targeting attributes are beneficial for this task.
GisPy: A Tool for Measuring Gist Inference Score in Text
TLDR
This work delineates the process of developing GisPy, an open-source tool in Python for measuring the Gist Inference Score (GIS) in text, and demonstrates that scores generated by the tool can distinguish low vs. high gist documents.
...
...