Tag Recommendation for Short Arabic Text by Using Latent Semantic Analysis of Wikipedia

AlAgha, Iyad; Samra, Yousef K. Abu

doi:10.5455/jjcit.71-1575827721

Cited by 3 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is a statistical text analytics method that can uncover the conceptual content within unstructured data by using Singular Value Decomposition (SVD). Several works have used LSA to measure similarity between terms [22,23]. Hyperspace Analogue to Language (HAL) is another corpusbased method that captures the statistical dependencies between terms by considering their co-occurrences in a surrounding window of text [24,25].…”

Section: B Corpus-based Similarity Methodsmentioning

confidence: 99%

“…Others used Wikipedia features and hyperlink structure to build Arabic-named entity corpora [49,50] or for entity linking [50]. Wikipedia-based categories have been also used to support the classification of Arabic text [51], the open-domain text tagging [23], and the search query expansion [52]. This work adds to the previous knowledge by leveraging the Arabic Wikipedia to measure semantic relatedness between Arabic terms.…”

Section: Arabic Semantic Similarity Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting Wikipedia to Measure the Semantic Relatedness between Arabic Terms

2022

JERT

View full text Add to dashboard Cite

Measuring the semantic relatedness between words or terms plays an important role in many domains such as linguistics and artificial intelligence. Although this topic has been widely explored in the literature, most efforts focused on the English text, while little has been done to measure the similarity between Arabic terms. A growing number of semantic relatedness measures have relied on an underlying background knowledge such as Wikipedia. They often map terms to Wikipedia concepts, and then use the content or hyperlink structure of the corresponding Wikipedia articles to estimate the similarity between terms. However, existing approaches mostly focused on the English version of Wikipedia, while limited work has been done on the Arabic version. This work proposes an approach that takes advantage of Wikipedia features to measure the relationship between Arabic terms. It exploits two types of relations to gain rich features for the similarity measure, which are: the context-based relation and the category-based relation. The context-based relation is measured based on the intersection between incoming links of Wikipedia articles, while the category-based relation is measured by utilizing the taxonomy of Wikipedia categories. The proposed approach was evaluated based on a translated version of the WordSimilarity-353 benchmark dataset. The results show that our approach generally outperforms several approaches in the literature that use the same dataset in English. However, the poor structure and content of the Arabic version of Wikipedia compared to the English version has resulted in several incorrect similarity scores.

show abstract

Section: B Corpus-based Similarity Methodsmentioning

confidence: 99%

Section: Arabic Semantic Similarity Methodsmentioning

confidence: 99%

Exploiting Wikipedia to Measure the Semantic Relatedness between Arabic Terms

2022

JERT

View full text Add to dashboard Cite

show abstract

“…Stopword biasanya merupakan kata penghubung antar kalimat, dalam kasus ini stopword menggunakan kata-kata 'and','for','in','a','of','the','to', 'on'. 'fisheries': [0], 'republic': [0], 'indonesia': [0], 'assessing': [1], 'application': [1,8], 'portfolios': [1], 'it': [1,1], 'services': [1], 'through': [1], 'maturity': [1], 'levels': [1], 'governance': [1], 'scientific': [2], 'article': [2], 'clustering': [2], 'string': [2], 'similarity': [2], 'concept': [2], 'audit': [3], 'provincial': [3], 'library': [3], 'information': [3,4], 'system': [3], 'based': [3,8], 'cobit': [3], '4.1': [3], 'impact': [4], 'between': [4], 'use': [4,5], 'technology,': [4], 'user': [4,4], 'ability': [4], 'motivation': [4], 'employee': [4], 'performance': [4,6], 'koperasi': [4], 'kuta': [4], 'mimba': [4], 'mediating': [5], 'role': [5], 'intention': [5], 'e-commerce':…”

Section: Analisis Metode Lsamentioning

confidence: 99%

“…Untuk mempermudah proses pencarian data, berbagai macam metode dikembangkan. Salah satu metode yang dapat digunakan dalam proses pencarian data adalah Latent Semantic Analysis (LSA) yang dapat digunakan dalam tag recommendation [2], movie recommendation [3], keyword extraction [4] dan lain sebagainya. Sehingga pengembangan query suggestion menggunakan LSA dapat dilakukan untuk mempermudah proses pencarian data.…”

unclassified

Penerapan LSA dan Query Suggestion untuk Pencarian Judul Artikel Menggunakan Framework FLASK

Negara

Kartika

2022

CogITo Smart Journal

View full text Add to dashboard Cite

Pencarian informasi melalui web sudah sangat berkembang seiring dengan dukungan perkembangan perangkat keras. Untuk mempermudah proses pencarian data, berbagai macam metode dikembangkan untuk pencarian informasi menggunakan data pencarian yang tersimpan pada browser ataupun menggunakan data yang terdapat di dalam database. Pengembangan query suggestion menggunakan Latent Semantic Analysis dapat dilakukan untuk mempermudah proses pencarian data. Penelitian ini dilakukan dengan menggunakan metode analisis sederhana yaitu dengan menganalisis metode Latent Semantic Analysis, Implementasi, Pengujian program dan analisis hasil query suggestion menggunakan metode tersebut. Data yang digunakan dalam penelitian ini adalah data publikasi yang telah dilaksanakan pada ICORIS 2019 sebagai data uji sebanyak 55 artikel. System diimplementasikan berbasis web menggunakan FLASK framework dan bahasa pemrograman python serta database MySQL. Adapun hasil dari penelitian ini adalah, semakin lengkap kata kunci yang dimasukkan, akan mendapatkan nilai similarity yang semakin tinggi untuk data target yang sesuai. Namun jumlah suggestion akan bertambah sesuai dengan data yang ada. Pada hasil penelitian, urutan kata kunci yang dicari tidak berpengaruh pada pemberian saran pencarian, karena data pencarian dan data didalam database dibandingkan berdasarkan kata-kata yang ada. Serta waktu proses yang didapatkan untuk pemberian suggestion adalah kurang dari 1 menit untuk 55 data judul yang digunakanKata kunci— Query Suggestion, FLASK, Python, MySQL, Latent Semantic Analisys

show abstract

“…They have surpassed classical machine learning approaches in various text classification tasks. Existing methods from the literature have often tackled the problem of short text classification by extending the short text with information retrieved from search engines [7, 8] [9] or external knowledge bases such as Wikipedia, and WordNet [10][11][12][13]. The intention is to enrich the short text with related information that provides extra features to support the classification process.…”

Section: Introductionmentioning

confidence: 99%

Leveraging Knowledge-Based Features With Multilevel Attention Mechanisms for Short Arabic Text Classification

AlAgha

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the wide spread of short texts through social media platforms, there has become a growing need for effective methods for short-text classification. However, short-text classification has always been challenging due to the ambiguity and the data sparsity of the short text. A common solution is to enrich the short text with additional semantic features extracted from external knowledge, such as Wikipedia, to help the classifier better decide on the correct class. Most existing works, however, focused on text written in English and benefited from the existence of entity-linking tools based on English-based knowledge bases. When it comes to the Arabic language, the exploitation of external knowledge to support the classification of Arabic short text has not been widely explored. This work presents an approach for the classification of short Arabic text that exploits both the Wikipedia-based features and the attention mechanism for effective classification. First, Wikipedia entities mentioned in the short text are identified. Then, Wikipedia categories associated with the identified entities are retrieved and filtered to retain only the most relevant categories. A deep learning model with multiple attention mechanisms is then used to encode the short text and the associated category set. Finally, the short text and category representations are combined together to be fed into the classification layer. The use of the attentive model with category filtering leads to highlighting the most important features while reducing the effect of improper features. Finally, the proposed model is evaluated by comparing it with several deep learning models.

show abstract

Tag Recommendation for Short Arabic Text by Using Latent Semantic Analysis of Wikipedia

Cited by 3 publications

References 0 publications

Exploiting Wikipedia to Measure the Semantic Relatedness between Arabic Terms

Exploiting Wikipedia to Measure the Semantic Relatedness between Arabic Terms

Penerapan LSA dan Query Suggestion untuk Pencarian Judul Artikel Menggunakan Framework FLASK

Leveraging Knowledge-Based Features With Multilevel Attention Mechanisms for Short Arabic Text Classification

Contact Info

Product

Resources

About