A novel robust Arabic light stemmer

While significant progress has been achieved for Opinion Mining in Arabic (OMA), very limited efforts have been put towards the task of Emotion mining in Arabic. In fact, businesses are interested in learning a fine-grained representation of how users are feeling towards their products or services. In this work, we describe the methods used by the team Emotion Mining in Arabic (EMA), as part of the SemEval-2018 Task 1 for Affect Mining for Arabic tweets. EMA participated in all 5 subtasks. For the five tasks, several preprocessing steps were evaluated and eventually the best system included diacritics removal, elongation adjustment, replacement of emojis by the corresponding Arabic word, character normalization and light stemming. Moreover, several features were evaluated along with different classification and regression techniques. For the 5 subtasks, word embeddings feature turned out to perform best along with Ensemble technique. EMA achieved the 1 st place in subtask 5, and 3 rd place in subtasks 1 and 3.

show abstract

“…The lexicon consisted of 100 emojis. The tweets were finally stemmed using A Robust Arabic Light Stemmer (ARLSTEM) (Abainia et al, 2017).…”

Section: Preprocessingmentioning

confidence: 99%

EMA at SemEval-2018 Task 1: Emotion Mining for Arabic

Badaro¹,

Jundi²,

Khaddaj³

et al. 2018

Proceedings of the 12th International Workshop on Semantic Evaluation

View full text Add to dashboard Cite

show abstract

“…Abainia et al [18] built a novel Arabic Light Stemmer (ARLStem) based on stripping prefixes, suffixes, and infixes from the words. They determine that their work is the first work that deals with remove infixes and their results outperform many present light stemmers.…”

Section: Kanan and Foxmentioning

confidence: 99%

“…The light stemming technique is not meant to retrieve the root of a selected Arabic word; hence, this technique is not meant for dealing with infixes or recognize patterns. Many light stemmers have been recommended for the Arabic language [18]. With regards to the light stemmer, its technique gets rid of affixes, predefined in the list, without finding it out if the leftover is a stem.…”

Section: ) Stemming Techniquesmentioning

confidence: 99%

“…Again, there is an indefinite list of these removable affixes [43]. For instance, Tashaphyne [44], and ARLStem [18] are two stemmers that employ light stemming technique. To be more precise, Tashaphyne stemmer works by first normalizing words in preparation for the ''search and index'' tasks that require stemming.…”

Section: ) Stemming Techniquesmentioning

confidence: 99%

“…Many researchers investigated various Arabic stemming techniques to enhance the performance of Arabic DC. This paper presents the results of an experiment by comparing three stemmers which are Information Science Research Institute stemmer (ISRI) [16], Tashaphyne [17] and Arabic light stemmer (ARLStem) [18] on Arabic DC. The study is the first of its kind that deals with the ARLStem stemmer on Arabic DC, especially with public dataset such as CNN dataset collected by Saad and Ashour [19] according to the background search.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Study of the Effects of Stemming Strategies on Arabic Document Classification

et al. 2019

View full text Add to dashboard Cite

Stemming is one of the most effective techniques, which has been adopted in many applications, such as machine learning, machine translation, document classification (DC), information retrieval, and natural language processing. The stemming technique is meant to be applied during the classification of documents to reduce the high dimensionality of the feature space, which, in turn, raises the functioning of the classification system, particularly with extreme modulated language, for instance, Arabic language. This paper aims to study the impact of stemming techniques, namely Information Science Research Institute (ISRI), Tashaphyne, and ARLStem on Arabic DC. The classification algorithms, namely Naïve Bayesian (NB), support vector machine (SVM), and K-nearest neighbors (KNN), are used in this paper. In addition, the chi-square feature selection is used to select the most relevant features. Experiments are conducted on CNN Arabic corpus, which is collected from Arabic websites to assess the performance of the classification system. In order to evaluate the classifiers, the K-fold cross-validation method and Micro-F1 are used. Findings of this paper indicate that the ARLStem outperforms the ISRI and Tashaphyne stemmers. The outcomes clearly showed the effectiveness of the SVM over the KNN and NB classifiers, which achieved 94.64% Micro-F1 value when using the ARLStem stemmer. INDEX TERMS Arabic text classification, text preprocessing, stemming techniques, feature extraction, feature selection.

show abstract