AI-Based Cyberbullying Prevention in 5G Networks

2020 ◽  
Vol 11 (4) ◽  
pp. 1-20
Author(s):  
Sara Ramezanian ◽  
Tommi Meskanen ◽  
Valtteri Niemi
Keyword(s):  
Social Media ◽  
Psychological Effects ◽  
5G Networks ◽  
Inverse Document Frequency ◽  
Term Frequency ◽  
Online Social Media ◽  
Document Frequency ◽  
Policy Control ◽  
Cyberbullying Detection ◽  
Victims Of Bullying

Children and teenagers that have been victims of bullying can possibly suffer its psychological effects for a lifetime. With the increase of online social media, cyberbullying incidents have been increased as well. In this paper, the authors discuss how they can detect cyberbullying with AI techniques, using term frequency-inverse document frequency. The authors label messages as benign or bully. The authors want their method of cyberbullying detection to be privacy-preserving, such that the subscribers' benign messages should not be revealed to the operator. Moreover, the operator labels subscribers as normal, bully, and victim. The operator utilizes policy control in 5G networks to protect victims of cyberbullying from harmful traffic.

Exploiting user network topology and comment semantic for accurate rumour stance recognition on social media

2020 ◽  
pp. 016555152097744
Author(s):  
Yongcong Luo ◽  
Jing Ma ◽  
Chai Kiat Yeo
Keyword(s):  
Social Media ◽  
Network Topology ◽  
Semantic Representation ◽  
Fake News ◽  
Inverse Document Frequency ◽  
Online Social Media ◽  
Document Frequency ◽  
Rapid Dissemination ◽  
Sentiment Score ◽  
Vector Matrix

Online social media (OSM) has become a hotbed for the rapid dissemination of disinformation or fake news. In order to recognise fake news and guide users of OSM, we focus on the stance recognition of comments, posted on OSM on the fake news-related users. In this article, we propose a framework for recognition of rumour stances (we set four categories –‘agree’, ‘disagree’, ‘neutral’ and ‘query’), combining network topology and comment semantic enhancement (CSE). We first construct a vector matrix of comments via a novel optimised term frequency–inverse document frequency (OTI). To better recognise stances, we employ another vector matrix with novel or special attributes which comprises the network topology of the OSM users derived from the random walk with restart (RWR) method. In addition, we set a weight parameter for each word in the comments to enhance comment semantic representation, where these parameters are tuned based on sentiment score, topology features and question format words. These vector matrices are optimised and combined into an integrated matrix whose transpose matrix is fed into a neural network (NN) for final rumour stance recognition. Experimental evaluations show that our approach achieves a high precision of 93.96% and F1-score of 92.02% which are superior to baselines and other existing methods.

Identification of rumour stances by considering network topology and social media comments

2020 ◽  
pp. 016555152094435
Author(s):  
Yongcong Luo ◽  
Jing Ma ◽  
Chai Kiat Yeo
Keyword(s):  
Social Media ◽  
Network Topology ◽  
Inverse Document Frequency ◽  
Online Social Media ◽  
Document Frequency ◽  
The Matrix ◽  
Special Attribute ◽  
Rapid Dissemination ◽  
Two Parameters ◽  
Vector Matrix

Online social media (OSM) has become a hotbed for the rapid dissemination of disinformation or faked news. In order to track and limit the spread of faked news, we study stance identification of comments posted on OSM, where the stance can denote the comment’s semantics. In this article, we propose a framework for identification of rumour stances, combining network topology and OSM comments. We construct a vector matrix of comments and words via OTI (optimisation term frequency–inverse document frequency). To better identify the stances, we introduce another vector matrix with novel or special attribute, that is, network topology among the users. Variant autoencoder (VAE) is then applied for dimensionality reduction and optimisation of these vector matrices which are then combined into an integrated matrix [Formula: see text], tempered by two parameters [Formula: see text] and [Formula: see text]. Finally, the matrix is fed into a neural network for final rumour stance identification. Experimental evaluations show that our proposed approach outperforms some state-of-the-art methods and achieves a high precision of 90.26% and F1-score of 88.58%.

scholarly journals Sistem Rekomendasi Produk Pena Eksklusif Menggunakan Metode Content-Based Filtering dan TF-IDF

2020 ◽  
Vol 5 (3) ◽  
pp. 229
Author(s):  
Mariani Widia Putri ◽  
Achmad Muchayan ◽  
Made Kamisutara
Keyword(s):  
Information Retrieval ◽  
Customer Relationship Management ◽  
Relationship Management ◽  
Customer Relationship ◽  
Brand Awareness ◽  
Product Knowledge ◽  
Inverse Document Frequency ◽  
Term Frequency ◽  
Document Frequency ◽  
Content Based Filtering

Sistem rekomendasi saat ini sedang menjadi tren. Kebiasaan masyarakat yang saat ini lebih mengandalkan transaksi secara online dengan berbagai alasan pribadi. Sistem rekomendasi menawarkan cara yang lebih mudah dan cepat sehingga pengguna tidak perlu meluangkan waktu terlalu banyak untuk menemukan barang yang diinginkan. Persaingan antar pelaku bisnis pun berubah sehingga harus mengubah pendekatan agar bisa menjangkau calon pelanggan. Oleh karena itu dibutuhkan sebuah sistem yang dapat menunjang hal tersebut. Maka dalam penelitian ini, penulis membangun sistem rekomendasi produk menggunakan metode Content-Based Filtering dan Term Frequency Inverse Document Frequency (TF-IDF) dari model Information Retrieval (IR). Untuk memperoleh hasil yang efisien dan sesuai dengan kebutuhan solusi dalam meningkatkan Customer Relationship Management (CRM). Sistem rekomendasi dibangun dan diterapkan sebagai solusi agar dapat meningkatkan brand awareness pelanggan dan meminimalisir terjadinya gagal transaksi di karenakan kurang nya informasi yang dapat disampaikan secara langsung atau offline. Data yang digunakan terdiri dari 258 kode produk produk yang yang masing-masing memiliki delapan kategori dan 33 kata kunci pembentuk sesuai dengan product knowledge perusahaan. Hasil perhitungan TF-IDF menunjukkan nilai bobot 13,854 saat menampilkan rekomendasi produk terbaik pertama, dan memiliki keakuratan sebesar 96,5% dalam memberikan rekomendasi pena.

scholarly journals Hitek és tévhitek a növényi alapú étrendről egy online kutatás eredményei alapján

2020 ◽  
Vol 7 (2) ◽  
pp. 65-77
Author(s):  
Veronika Keller ◽  
◽  
Viktória Bocsková ◽  
Keyword(s):  
Social Media ◽  
Online Survey ◽  
Healthy Lifestyle ◽  
Current Trend ◽  
Psychological Effects ◽  
Fruit And Vegetables ◽  
Online Social Media ◽  
Significant Relationships ◽  
The Earth ◽  
Different Types

A main current trend is healthy lifestyle and the consumption of fruit and vegetables. The assessment of healthiness of plant-based diet is not so obvious either among the population or food experts. In an online survey the knowledge, beliefs and misbeliefs about plant-based diet were analysed among members and non-members of online social media lifestyles groups. All in all, it can be stated that there are no significant relationships and differences between knowledge, attitude and perception of members and non-members. Social media users are aware of the different types of plant-based diet (vegetarian, vegan) and the positive and negative psychological effects. The associations connected to plant-based diet are the following: healthy, environmentally friendly and expensive. Only a small segment of Hungarian people follow plant-based diet. At the same the diverse and everyday consumption of fruit and vegetables is essential because of health and sustainability issues. Due to conscious nutrition and more plant-based diet, people can contribute to the protection of their own health and the Earth.

scholarly journals Seleksi Fitur Bobot Kata dengan Metode TFIDF untuk Ringkasan Bahasa Indonesia

2018 ◽  
pp. 119
Author(s):  
Ni Komang Widyasanti ◽  
I Ketut Gede Darma Putra ◽  
Ni Kadek Dwi Rusjayanthi
Keyword(s):  
Inverse Document Frequency ◽  
Term Frequency ◽  
Document Frequency ◽  
Bahasa Indonesia

Penyebaran informasi dalam bentuk teks digital semakin tak terbendung seiring perkembangan waktu. Kebutuhan akan membaca informasi juga tidak pernah berkurang, berdasarkan riset yang dilakukan pada lima kota besar di Indonesia sepanjang tahun 2015 oleh okezone.com menyatakan persentasi konsumsi berita secara online mencapai 96%. Salah satu solusi untuk mempermudah dan mempercepat pencarian informasi yang sesuai adalah dengan meringkas konten tersebut. TFIDF (Term Frequency Inverse Document Frequency) merupakan metode pembobotan dalam bentuk integrasi antar term frequency dengan inverse document frequency. Metode TFIDF digunakan pada penelitian ini untuk memilih fitur sebagai hasil ringkasan, dengan penerapannya pada seleksi fitur bobot kata. Nilai kepuasan pembaca sebesar 61,94%. Durasi ringkasan rata-rata 68,25 detik dengan jumlah kalimat dan kata rata-rata 31,875 dan 387,375. Penelitian dilakukan menggunakan jenis dokumen fiksi dan non-fiksi serta seleksi fitur disetiap paragrafnya, yang membedakannya dengan penelitian terkait sebelumnya. Kata Kunci: Ringkasan Teks Otomatis, Pembobotan TFIDF, Bahasa Indonesia

scholarly journals SMS Spam Message Detection using Term Frequency-Inverse Document Frequency and Random Forest Algorithm

2019 ◽  
Vol 161 ◽  
pp. 509-515 ◽  
Author(s):  
Nilam Nur Amir Sjarif ◽  
Nurulhuda Firdaus Mohd Azmi ◽  
Suriayati Chuprat ◽  
Haslina Md Sarkan ◽  
Yazriwati Yahya ◽  
...  
Keyword(s):  
Random Forest ◽  
Random Forest Algorithm ◽  
Inverse Document Frequency ◽  
Term Frequency ◽  
Document Frequency
Sign in / Sign up

Export Citation Format

Share Document