Arabic summarization in Twitter social network

El-Fishawy, Nawal; Hamouda, Alaa; Attiya, Gamal; Atef, Mohammed

doi:10.1016/j.asej.2013.11.002

Cited by 36 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Node rank score for node i , NR(n i ), is calculated from Equation , NH is the set of neighbors for the k ,

d_{out}^{ji}

is the distance of out link edges from node j to node i , PO(n i ) is the current energy of node i , and α is the damping factor. Recent studies have checked many damping factors (α) confirming that the suitable factor is 0.85 as mentioned in El‐Fishawy et al for Arabic summarization in Twitter social network.

italicNR ((), n_{i}) = italicPO {(n_{i})}^{*} α^{*} \sum_{0}^{j} italicNR ((), n_{j}) \frac{1 / {italicd}_{italicout}^{italicji}}{\sum_{k \in italicNH} d_{out}^{jk}} + ((), 1 - α) .

…”

Section: Our Proposed Protocol: Node Ranked–leachmentioning

confidence: 80%

A new algorithm for cluster head selection in LEACH protocol for wireless sensor networks

Al-Baz

El‐Sayed

2017

Int J Communication

150

View full text Add to dashboard Cite

SummaryIn wireless sensor network, a large number of sensor nodes are distributed to cover a certain area. Sensor node is little in size with restricted processing power, memory, and limited battery life. Because of restricted battery power, wireless sensor network needs to broaden the system lifetime by reducing the energy consumption. A clustering-based protocols adapt the use of energy by giving a balance to all nodes to become a cluster head. In this paper, we concentrate on a recent hierarchical routing protocols, which are depending on LEACH protocol to enhance its performance and increase the lifetime of wireless sensor network. So our enhanced protocol called Node Ranked-LEACH is proposed. Our proposed protocol improves the total network lifetime based on node rank algorithm. Node rank algorithm depends on both path cost and number of links between nodes to select the cluster head of each cluster. This enhancement reflects the real weight of specific node to success and can be represented as a cluster head. The proposed algorithm overcomes the random process selection, which leads to unexpected fail for some cluster heads in other LEACH versions, and it gives a good performance in the network lifetime and energy consumption comparing with previous version of LEACH protocols. KEYWORDScluster head selection, clustering-based protocols, LEACH protocols, wireless sensor networks | INTRODUCTIONWireless sensor networks (WSNs) consider a base station (BS) that communicates with countless of wireless sensor nodes by means of a radio channel. Data transmission and reception process are the major operations that consume power in WSN. Elimination of redundant data is important issue in WSN, because multiple nodes may sense the same overlapped area. This action will reduce the overall power consumption and use the bandwidth usage.Routing protocols in WSNs can be divided according to network structure into 3 categories: location based, data centric, and hierarchical protocols. 1,2 Location-based protocol: location information for all nodes is a major cornerstone during data communication. Energy consumption during data transmission depends on the target position distance. Data are sent not only to the target area but also to whole sensors network, which is known as flooding. Residual energy is not considered for each node, so many nodes will run out of energy, which leads at the end to an accumulative data transmission failure. [3][4][5] Data-centric protocol 6 : data transmission from sensor node to the BS through intermediate nodes. The intermediate node may not have interest in the data it receives-it is known as relay node in this case. This process reduces the number of packet sent from source to the sink, which leads to reduce the power consumption.

show abstract

“…Node rank score for node i , NR(n i ), is calculated from Equation , NH is the set of neighbors for the k ,

d_{out}^{ji}

italicNR ((), n_{i}) = italicPO {(n_{i})}^{*} α^{*} \sum_{0}^{j} italicNR ((), n_{j}) \frac{1 / {italicd}_{italicout}^{italicji}}{\sum_{k \in italicNH} d_{out}^{jk}} + ((), 1 - α) .

…”

Section: Our Proposed Protocol: Node Ranked–leachmentioning

confidence: 80%

A new algorithm for cluster head selection in LEACH protocol for wireless sensor networks

Al-Baz

El‐Sayed

2017

Int J Communication

150

View full text Add to dashboard Cite

show abstract

“…Topic detection enables the automatic identification of semantic content and the assignment of a topic label to a given document. Although these approaches are highly useful for a large spectrum of applications, only a limited number of documents with keywords are available online (El-Fishawy, 2014). Keyword extraction is also a process of identifying a short list of words or noun phrases that capture the most important ideas or topics covered in a document (Awajan, 2014).…”

Section: Related Workmentioning

confidence: 99%

Analysis of latent Dirichlet allocation and non-negative matrix factorization using latent semantic indexing

al.¹

2019

Int. j. adv. appl. sci.

View full text Add to dashboard Cite

A word is a major attribute in the field of opinion/text mining. Based on this attribute, it is decided that whether it is a keyword, aspect, feature, entity, title, or topic? Lots of work has been done to detect such targets using both supervised and unsupervised approaches. These targets can be used in further processing such as text analytics, sentiment analysis, information retrieval, and searches, etc. Latent Dirichlet allocation (LDA) and nonnegative matrix factorization (NMF) are the major models used for detecting topics. Understanding the depth and details of them algorithms are necessary for those who want to extend these models. The research community of opinion/text mining uses them as a black box. However, there is a question about which model is the most accurate for detecting topics. Latent semantic indexing (LSI) is the best approach for detecting the best match for document in a given query. In this study, we analyzed the LDA and NMF models using LSI to determine the best model for opinion/text mining and found that both are very good, but NMF is slightly better than LDA.

show abstract

“…Menurut Kaikhah (2004), dua faktor keupayaan teknik ringkasan teks iaitu pertama teknik ini berupaya mengurus hasil carian yang relevan dengan keperluan maklumat pengguna dengan mudah, dan kedua teknik ini mampu mengurangkan kesukaran ketika pemilihan hasil carian yang relevan dalam kuantiti yang besar. Ketersediaan pelbagai dokumen digital dalam kuantiti yang besar dalam sistem capaian maklumat mendorong kepada penyelidikan aktif teknik ringkasan teks seperti kajian Alguliev (2011), Atkinson dan Munoz (2013), dan El-Fishawy et al (2014).…”

Section: Kajian Lepas Teknik Ringkasan Teksunclassified

Penjanaan Ringkasan Isi Utama Berita Bahasa Melayu berdasarkan Ciri Kata (Generation of News Headline for Malay Language based on Term Features)

Noah

Ali

Hasan

2018

GEMA

View full text Add to dashboard Cite

Headline generation is an information extraction process to generate a single sentence that represents the content of a text. In Malay language context, research in this area is limited to machine translation approaches. This study is divided into three phases: analysis of news discourse, development of headline generation technique and evaluation of the quality of generated headlines. The study aims to develop headline using statistical and linguistic methods. The statistic method used to identify significant words and sentences based in term weighting approach. The linguistic method is used to increase its preciseness. 140 news and their corresponding headlines model were constructed. Analysis of the news collection shows that the main idea of written text can be identified based on four characteristics: word location in sentences, sentence location in texts, acronym word types and words that represent the person name. Significant words with main idea of written text are determined based on the words weighted values. The values are determined by combining the frequency of words and word location in sentences. The content of the first two sentences are suitable candidates for recognising important sentences in text. Results showed that mean percentage for important sentence recognition 82.9%, mean quality of generated headlines are 0.3194 (precision), 0.5656 (recall), 0.4012 (F-measure), 0.5656 (ROUGE-N), 0.3392 (ROUGE-L), 0.1186 (ROUGE-W) and 0.1232 (ROUGE-S). In conclusion, the consideration of language factors in headline generation technique is capable of producing quality headlines with higher degree of fidelity as compared to the compared benchmarks.

show abstract

Arabic summarization in Twitter social network

Cited by 36 publications

References 11 publications

A new algorithm for cluster head selection in LEACH protocol for wireless sensor networks

A new algorithm for cluster head selection in LEACH protocol for wireless sensor networks

Analysis of latent Dirichlet allocation and non-negative matrix factorization using latent semantic indexing

Penjanaan Ringkasan Isi Utama Berita Bahasa Melayu berdasarkan Ciri Kata (Generation of News Headline for Malay Language based on Term Features)

Contact Info

Product

Resources

About