Muhammad Abdul-Mageed

SAMAR: Subjectivity and sentiment analysis for Arabic social media

SAMAR is a system for subjectivity and sentiment analysis (SSA) for Arabic social media genres. Arabic is a morphologically rich language, which presents significant complexities for standard approaches to building SSA systems designed for the English language. Apart from the difficulties presented by the social media genres processing, the Arabic language inherently has a high number of variable word forms leading to data sparsity. In this context, we address the following 4 pertinent issues: how to best represent lexical information; whether standard features used for English are useful for Arabic; how to handle Arabic dialects; and, whether genre specific features have a measurable impact on performance. Our results show that using either lemma or lexeme information is helpful, as well as using the two part of speech tagsets (RTS and ERTS). However, the results show that we need individualized solutions for each genre and task, but that lemmatization and the ERTS POS tagset are present in a majority of the settings.

Subjectivity and Sentiment Analysis of Arabic: A Survey

Subjectivity and sentiment analysis (SSA) has recently gained considerable attention, but most of the resources and systems built so far are tailored to English and other Indo-European languages. The need for designing systems for other languages is increasing, especially as blogging and micro-blogging websites become popular throughout the world. This paper surveys different techniques for SSA for Arabic. After a brief synopsis about Arabic, we describe the main existing techniques and test corpora for Arabic SSA that have been introduced in the literature.

EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks

Accurate detection of emotion from natural language has applications ranging from building emotional chatbots to better understanding individuals and their lives. However, progress on emotion detection has been hampered by the absence of large labeled datasets. In this work, we build a very large dataset for fine-grained emotions and develop deep learning models on it. We achieve a new state-of-the-art on 24 fine-grained types of emotions (with an average accuracy of 87.58%). We also extend the task beyond emotion types to model Robert Plutick’s 8 primary emotion dimensions, acquiring a superior accuracy of 95.68%.

Does ‘well-being’ translate on Twitter?

We investigate whether psychological wellbeing translates across English and Spanish Twitter, by building and comparing source language and automatically translated weighted lexica in English and Spanish. We find that the source language models perform substantially better than the machine translated versions. Moreover, manually correcting translation errors does not improve model performance, suggesting that meaningful cultural information is being lost in translation. Further work is needed to clarify when automatic translation of well-being lexica is effective and how it can be improved for crosscultural analysis.

Automatic Detection of Arabic Non-Anaphoric Pronouns for Improving Anaphora Resolution

Anaphora resolution is one of the most difficult tasks in NLP. The ability to identify non-referential pronouns before attempting an anaphora resolution task would be significant, since the system would not have to attempt resolving such pronouns and hence end up with fewer errors. In addition, the number of non-referential pronouns has been found to be non-trivial in many domains. The task of detecting non-referential pronouns could also be incorporated into a part-of-speech tagger or a parser, or treated as an initial step in semantic interpretation. In this article, I describe a machine learning method for identifying non-referential pronouns in an annotated subsegment of the Penn Arabic Treebank using three different feature settings. I achieve an accuracy of 97.22% with 52 different features extracted from a small window size of -5/+5 tokens surrounding each potentially non-referential pronoun.

Not All Segments are Created Equal: Syntactically Motivated Sentiment Analysis in Lexical Space.

Although there is by now a considerable amount of research on subjectivity and sentiment analysis on morphologicallyrich languages, it is still unclear how lexical information can best be modeled in these languages. To bridge this gap, we build effective models exploiting exclusively gold and machine-segmented lexical input and successfully employ syntactically motivated feature selection to improve classification. Our best models achieve significantly above the baselines, with 67.93% and 69.37% accuracies for subjectivity and sentiment classification respectively.

A Multilevel Investigation of Arabic-Language Impression Change

This research investigates how impressions are formed from simple social events described in the Arabic language. Multilevel data enable us to investigate the degree of cultural consensus in how native Arabic-speakers currently living in North Carolina view social events. These data allow us to investigate a core assumption of affect control theory—that affective responses to social events are shared within a language culture. The results of hierarchical linear modeling suggest little variation in the constant and stability effects during event processing among these Arabic-speakers from very diverse backgrounds. Evaluation constants and stability effects show no significant individual-level variation and can be described by a simple event-level model. In particular, evaluation processing is similar for Arabic-speaking men and women and for Muslims and Christians. Potency and activity dynamics show slight differences by gender and religion. We then proceed to estimate Arabic evaluation dynamics using regression techniques, and compare them to U.S. English equations. Arabic equations are consistently simpler than U.S. English ones, and stability effects are consistently smaller. In the Arabic equations, nice behaviors make actors seem more powerful, while the reverse is true in U.S. English equations. In general, the object of an action appears to be more important in Arabic than in English impression-change models.