Classifying Suspicious Twitter Content using Naïve Bayes And Random Forest Tree Methods

الموضوعات

علوم تطبيقية وتكنولوجية

الملخص

With the emergence and expansion of web technologies, now containing a huge amount of data and information for users, the Internet has evolved into platforms for dating and exchanging information, opinions, and ideasTwitter and other social networks are rapidly gaining popularity as they encourage users to communicate and convey their opinions on a variety of topics, engage in discussions with different cultures, and send messages around the world. Accordingly, this study aims to classify suspicious content on the Twitter platform in English and apply sentiment analysis (SA) technology to Twitter contents and use text mining techniques, which are useful for analyzing details in tweets where opinions are highly disorganized and heterogeneous and either negative, positive or neutral.The proposed system consists of five main stages ,The first stage is the data The group containing tweets from Twitter. And the second stage is Preprocessing the data is made by applying different step, The third stage involves sentiment analysis (SA) technology with extracting and selecting features using the term Document Inverted Frequency Approach (TF-IDF).And the fourth stage is Classification methods were applied using the Naive Bayes classifier (NB),and random forest (RF)Techniques have been implemented to highlight the most accurate ones Used to classify SMN data, and in the fifth stage, classification results Algorithms were evaluated based on a performance scale using precision,Accuracy, recall, and f1-score measurements. The results showed that The highest accuracy was achieved by implementing RFC of 92.61 and NB with the accuracy of 88.07, which is very good when compared with recent research.

روابط وملفات

التعريف والنوع

رقم الوثيقة

089e8160-ac83-412d-9a01-9e6adc7163c6

رقم العقد

0

نوع الوسائط

Crawler

نوع المحتوى

الرسائل العلمية

صيغة المصدر

رسائل ماجيستير

نوع الملف

pdf text

أسماء الملفات

996195_1.pdf

بيانات النشر

ألقاب المؤلفين

[{"name_ar":"حيدر حبيب","title_ar":"اشراف","title_en":"Supervision"},{"name_ar":"نور علوان غانم","title_ar":"اعداد","title_en":"Preparation"}]

اللغة

English

المصدر والدورية

اسم المصدر

Classifying Suspicious Twitter Content using Naïve Bayes And Random Forest Tree Methods

المحتوى والصفحات

عدد الصفحات

0

كلمات الباحثين

web technologies, Internet, social networks, Twitter, suspicious content, sentiment analysis, text mining, tweets, data preprocessing, TF-IDF, Naive Bayes, random forest, classification, accuracy, precision, recall, F1-score

إشراف وإعداد

الإشراف

حيدر حبيب

الإعداد

نور علوان غانم

الاقتباسات الببليوغرافية