scispace - formally typeset
Search or ask a question
Author

Mohammed H. Haggag

Bio: Mohammed H. Haggag is an academic researcher from Helwan University. The author has contributed to research in topics: Credibility & Support vector machine. The author has an hindex of 3, co-authored 7 publications receiving 28 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: A classification model based on supervised machine learning techniques and word-based N-gram analysis to classify Twitter messages automatically into credible and not credible and experiments show that the proposed model achieved an improvement when compared to two models existing in the literature.
Abstract: With the evolution of social media platforms, the Internet is used as a source for obtaining news about current events. Recently, Twitter has become one of the most popular social media platforms that allows public users to share the news. The platform is growing rapidly especially among young people who may be influenced by the information from anonymous sources. Therefore, predicting the credibility of news in Twitter becomes a necessity especially in the case of emergencies. This paper introduces a classification model based on supervised machine learning techniques and word-based N-gram analysis to classify Twitter messages automatically into credible and not credible. Five different supervised classification techniques are applied and compared namely: Linear Support Vector Machines (LSVM), Logistic Regression (LR), Random Forests (RF), Naïve Bayes (NB) and K-Nearest Neighbors (KNN). The research investigates two feature representations (TF and TF-IDF) and different word N-gram ranges. For model training and testing, 10-fold cross validation is performed on two datasets in different languages (English and Arabic). The best performance is achieved using a combination of both unigrams and bigrams, LSVM as a classifier and TF-IDF as a feature extraction technique. The proposed model achieves 84.9% Accuracy, 86.6% Precision, 91.9% Recall, and 89% F-Measure on the English dataset. Regarding the Arabic dataset, the model achieves 73.2% Accuracy, 76.4% Precision, 80.7% Recall, and 78.5% F-Measure. The obtained results indicate that word N-gram features are more relevant for the credibility prediction compared with content and source-based features, also compared with character N-gram features. Experiments also show that the proposed model achieved an improvement when compared to two models existing in the literature.

29 citations

Proceedings ArticleDOI
01 Dec 2018
TL;DR: A classification model based on supervised machine learning techniques is proposed to detect credibility on Twitter using both content-based and source-based features and achieves improvement of 22% when compared to CRF which applies the same approach in terms of F1-measure.
Abstract: Twitter is the most popular micro-blogging medium that allows users to exchange short messages, provides a platform for public people to share the news. Nowadays, Twitter counts with an average of 328 million monthly active users and is growing rapidly. Detecting the credibility of shared information on Twitter becomes a necessity, especially during high impact events. In this paper a classification model based on supervised machine learning techniques is proposed to detect credibility. The proposed model uses an extensive set of features including both content-based and source-based features. The research compares the performance of five different machine learning classifiers using three feature sets: content based, source based and a combination of both sets. The best performance is achieved when using a combined set of features and applying Random Forests as a classifier with accuracy 78.4%, precision 79.6%, recall 91.6% and f1-measure 85.2%. Experiments also revealed that the proposed model achieves improvement of 22% when compared to CRF which applies the same approach in terms of F1-measure. Feature analysis is presented to highlight the importance of the source-based features compared with the content-based features as deciders for credibility.

16 citations

Proceedings Article
01 Jan 2008
TL;DR: The experimental results proved that the efficiency of document clustering using WSD increases linearly with the size of the documents dataset, and different part of speech taggers were tested to determine the best.
Abstract: In computational linguistics, word sense disambiguation (WSD) is the problem of determining in which sense a word having a number of distinct senses is used in a given sentence . This paper handles text document clustering as one of the major tasks of text processing. Document clustering is the process of finding out groups of information from the text documents and cluster these documents into the most relevant groups. Large document corpus suffers from ambiguity problems like synonyms, polysemous and other semantic relations. For this reason we perform WSD task for all terms in all documents to get the best sense to be used as document features in the clustering process. Our experimental results proved that the efficiency of document clustering using WSD increases linearly with the size of the documents dataset. Different part of speech (POS) taggers were tested to determine the best; also the effect of different window sizes on WSD task was compared.

5 citations

Journal ArticleDOI
01 Jan 2015
TL;DR: Results of this present study indicated that aqueous extracts of Cymbopogon citratus has antinephrotoxic properties against cisplatin induced renal oxidative damage in rats which might be ascribed to its antioxidant and free radical scavenging property.
Abstract: The present study was conducted in order to examine the protective effect of lemon grass (Cymbopogon citratus) water extract (LGWE) against nephrotoxicity induced by cisplatin of male Albino rats. Thirty five adult male Albino rats weighing between 120-140g were randomly separated into five different groups (7rats each). Groupl was a normal control group (-ve), fed on basal diet. Group 2 was the positive control group (+ve) fed on basal diet for 6 weeks and then injected intraperitoneally (i.p.) with a single dose of cisplatin 5mg/kg of body weight. Groups 3, 4 and 5 fed the same as group2 and received 5, 7.5 and 10% lemon grass water extract, respectively, for 6 weeks and then injected intraperitoneally (i.p.) with the same dose of cisplatin. Five days later all rats in all groups were sacrificed and the blood was collected for biochemical and histopathological investigations. Cisplatin treatment caused significantly increase in serum malondialdehyde, uric acid, blood urea nitrogen and creatinine as well as alanine aminotransferase, aspartate aminotransferase and alkaline phosphatase (p<0.05) in +ve control group compared to —ve control group. Rats which were fed LGWE (groups 3, 4 and 5) showed marked reduction in the same biochemical investigations compared to +ve control group. Reduced glutathione (GSH), serum sodium and potassium mean values were decreased in +ve control group compared to —ve control rats. Feeding LGWE in groups 3, 4 and 5 showed a rise in the same biochemical parameters compared to +ve control group. 2, 2-Dipheny1-1-picrylhydrazyl (DPPH), half maximal inhibitory concentration (ICH) and total phenolic content of lemon grass was assayed. Parallel to the above mentioned changes, cisplatin treatment enhances renal damage as evidenced by sharp impairment of kidney function corresponds to biochemical parameters and histopathological findings. Additionally, feeding LGWE caused gradually histopathological improvement in renal tissues in groups 3, 4 and 5. These results of this present study indicated that aqueous extracts of Cymbopogon citratus has antinephrotoxic properties against cisplatin induced renal oxidative damage in rats which might be ascribed to its antioxidant and free radical scavenging property. According to these above results, it is recommended to conduct further studies on the use of LGWE and possible protection of human beings against nephrotoxicity.

2 citations

Journal ArticleDOI
01 Jul 2020
TL;DR: Results clarified that glomerular filtration rate (GFR) increased, while erythrocyte sedimentation rate (ESR) and C-reactive protein (CRP) significantly decreased in all treated patients compared to the control group, and the mixture of aqueous extracts of marjoram and sage recorded the best drink.
Abstract: Chronic kidney disease (CKD) is a worldwide public health problem. Oxidative stress is the causative factor for a wide variety of diseases, including CKD.Medicinal plants used in the management of CKD are effective in renal detoxification and help the effects of dialysis treatment.This study was conducted to investigate the effect of aqueous extract of sage (Salvia Officinal) and marjoram (Origanum Majoranum) on advanced chronic kidney patients under dialysis. The experiment was carried out on sixty patients (40-50 years old), diagnosis based on detailed clinical history, clinical examination and other relevant biochemical investigations.The patients were divided into 6 groups (each group contain 10 CKD patients under treatment with (hemodialysis and regular medical treatment for 3 months)as followed: control patients were treated with regular medical treatment, other patients consumed aqueous extracts of (5g sage, 5g marjoram, 10g sage, 10g marjoram, mixture of 5g sage +5g marjoram) twice today respectively. Results illustrated that the aqueous extract of marjoram or sage are rich in antioxidants components (Phenolic acids, Flavonoids, Oxygenated monoterpenes, Diterpenoids and Triterpenes), antioxidant capacity and phenolic content.Results clarify that glomerular filtration rate (GFR) increased, while erythrocyte sedimentation rate (ESR) and C-reactive protein (CRP) significantly decreased (P<0.05) in all treated patients compared to the control group. Malondialdehyde (MDA) decreased and superoxide dismutase (SOD) increased. The mixture of aqueous extracts of marjoram (5g) and sage (5g) recorded the best drink. Therefore, this study recommends the use of the aqueous extracts of marjoram (5g) and sage (5g) in decreasing the oxidative stress and improve kidney health in hemodialysis patients.

1 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: This paper reports a systematic mapping about semantics-concerned text mining studies that demonstrates that, although several studies have been developed, the processing of semantic aspects in text mining remains an open research problem.
Abstract: As text semantics has an important role in text meaning, the term semantics has been seen in a vast sort of text mining studies. However, there is a lack of studies that integrate the different research branches and summarize the developed works. This paper reports a systematic mapping about semantics-concerned text mining studies. This systematic mapping study followed a well-defined protocol. Its results were based on 1693 studies, selected among 3984 studies identified in five digital libraries. The produced mapping gives a general summary of the subject, points some areas that lacks the development of primary or secondary studies, and can be a guide for researchers working with semantics-concerned text mining. It demonstrates that, although several studies have been developed, the processing of semantic aspects in text mining remains an open research problem.

44 citations

Journal ArticleDOI
TL;DR: In this article, the authors present the present body of knowledge on the application of such intelligent tools in the fight against disinformation, and propose solutions based solely on the work of experts.

40 citations

Journal ArticleDOI
TL;DR: The prevalence and evolution of facets of social distancing during the COVID-19 pandemic in the US in a spatiotemporal context are defined and quantified and amplified tweets among social distanced facets are examined.

37 citations

Book ChapterDOI
09 Jan 2020
TL;DR: This paper proposes an approach which permits to evaluate information sources in term of credibility in Twitter, and relies on node2vec to extract features from twitter followers/followees graph and incorporates user features provided by Twitter.
Abstract: The quest for trustworthy, reliable and efficient sources of information has been a struggle long before the era of internet. However, social media unleashed an abundance of information and neglected the establishment of competent gatekeepers that would ensure information credibility. That’s why, great research efforts sought to remedy this shortcoming and propose approaches that would enable the detection of non-credible information as well as the identification of sources of fake news. In this paper, we propose an approach which permits to evaluate information sources in term of credibility in Twitter. Our approach relies on node2vec to extract features from twitter followers/followees graph. We also incorporate user features provided by Twitter. This hybrid approach considers both the characteristics of the user and his social graph. The results show that our approach consistently and significantly outperforms existent approaches limited to user features.

33 citations

17 Jul 2006
TL;DR: The COLING/ACL 2006 Interactive Presentations allowed developers of implemented computational linguistics software systems and libraries the opportunity to describe the design, development and functionality of their work in an interactive setting, and offered the presenters an opportunity to pro-actively engage more closely with the audience.
Abstract: The COLING/ACL 2006 Interactive Presentations took place on Monday 17th and Tuesday 18th July, 2006 as part of the joint conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics held in Sydney, Australia.The presentations allow developers of implemented computational linguistics software systems and libraries the opportunity to describe the design, development and functionality of their work in an interactive setting. It was also an opportunity to gain direct feedback from their users, and exchange ideas and development techniques with other developers.The presentations are the next iteration of the ongoing evolution of Demonstration and/or Interactive Poster sessions held at previous ACL annual meetings. Traditionally, the demonstrations have had an emphasis on mature systems and practical applications. Last year, Masaaki Nagata and Ted Pederson encouraged the dissemination of novel ideas supported by an implementation with the introduction of Interactive Posters.This year continued the emphasis on the interactive nature of this forum for developers of systems and libraries. The presentations were a combination of short conference-like talks and interactive demonstrations with audience involvement, questions and comments strongly encouraged. The session title Interactive Presentations was a challenge to the presenters --- to fully exploit the opportunity to pro-actively engage more closely with the audience.There were 31 proposals for interactive presentations submitted and 20 were accepted (an acceptance rate of 64.5%) after full peer review of the 4-page descriptions included in this volume and an additional 2-page presentation script. As well as the usual scholarship and technical criteria, the reviews took into consideration whether the software was available and ready to use, and the degree of interactivity proposed in the presentation script.

32 citations