<span lang="EN-US">This study describes the methods for eliminating irrelevant features in speech data to enhance toxic speech classification accuracy and reduce the complexity of the learning process. Therefore, the wrapper method is introduced to estimate the forward selection technique based on support vector machine (SVM) and random forest (RF) classifier algorithms. Eight main speech features were then extracted with derivatives consisting of 9 statistical sub-features from 72 features in the extraction process. Furthermore, Python is used to implement the classifier algorithm of 2,000 toxic data collected through the world's largest video sharing media, known as YouTube. Conclusively, this experiment shows that after the feature selection process, the classification performance using SVM and RF algorithms increases to an excellent extent. We were able to select 10 speech features out of 72 original feature sets using the forward feature selection method, with 99.5% classification accuracy using RF and 99.2% using SVM.</span>

Child exploitation by online paedophile is all over the world. Image, chat and audio-visual PENDAHULUANWonderland Club adalah nama sebuah weblog berbayar. Weblog ini berisi komunikasi para e-pedofilia untuk saling bertukar file bermuatan (content) porno dimana anak-anak menjadi obyek persepsi seksual. Persepsi seksual ditujukan pada situasi dimana para pengunjung menikmati visualisasi berupa foto (image) dan percakapan (posting message, chatting) tentang anak-anak dalam pose sensual (menampilkan hubungan sex atau anggota tubuh secara terbuka dengan penonjolan bagian tertentu) maupun natural (beraktivitas harian, misalnya tertawa, bermain). Kenikmatan yang dipersepsikan, kemudian menjadi pendorong bagi pengunjung website untuk melakukan tindakan (konasi) lanjutan berupa mengunduh file, berkomentar, melakukan kegiatan seks maupun mengunggah file koleksi pribadi. (Pavlik, 2004, p. 297). Weblog adalah "pages of short, frequently updated postings by an individual that are arranged chronologically, much like a series of diary entries or journal pages. Blogs can contain thoughts, links to sites o internets, rants, or whatever the blogger wants to write about"Pada tahun 1998 polisi Inggris bekerjasama dengan Amerika, Jerman, Italia, Norwegia, Finlandia, Belgia, Austria, Perancis, Swedia, dan Portugis menggelar operasi "Chatedral" untuk melacak jalur komunikasi para e-pedofilia yang walaupun berkumpul dalam "ring" pedofilia, keberadaan fisik mereka tersebar di beberapa Negara. Hasilnya adalah 11 orang tertangkap berasal dari Inggris, 32 dari Amerika, 18 dari Jerman, 16 dari Italia, dan 8 orang dari Negara sisanya. Sebagai "efek samping", para pelaku e-pedofilia belajar dari pengalaman dan menggunakan identitas"anonymous" untuk bergerilya di dunia maya dan mengelabui polisi.Pedofilia merupakan jenis kejahatan terhadap anak yang sudah lama terjadi di masyarakat. Melalui pengertian "an adult who is sexually attracted to a child or

No abstract

This study aims to determine the online public relations strategy for Akar Tuli Malang Community in campaigning the use of Indonesian sign language (BISINDO). BISINDO is a sign system used by Deaf in Indonesia to communicate. Akar Tuli Malang is the first Deaf community in East Java which is a place for Deaf and hearing friends to socialize. In carrying out its goals, Akar Tuli Malang has a public relations division that carries out the task of establishing cooperation with various parties, both internal and external. The method used in this research is a case study with a qualitative approach and is a type of descriptive research. The results of the study show that the design of a strategy that refers to the concept of a public relations strategy according to Pinkleton has six stages of strategy and the Malang Deaf Root has carried out five of them. Consists of conceptualization, monitoring, planning, organization and coordination, administration and evaluation. In carrying out the strategy online, PR utilizes social media Instagram as a medium for conveying campaign messages.

No abstract