Governments and social media providers put high effort to tackle massive negative contents in social media. Those contents are mostly containing religion, race, and inter-group issues, cyberbullying, and also body shamming, which usually appears together with offensive languages. It becomes difficult to overcome because of a large number of internet users in Indonesia. Hence, we need a system that can automatically detect the negative contents. This paper utilizes Neural Network (NN) models for not only classifying the words as (non)offensive words but also considering the structure of the sentence to get its context. There are two NN models analyzed in this paper: Artificial Neural Network (ANN) and Recurrent Neural Network (RNN). The computer simulation results show that the RNN has better performances than the ANN with the accuracy of training, validation, and testing 94%, 84%, and 84%, respectively. Pemerintah dan penyedia layanan media sosial di Indonesia berusaha keras untuk mengatasi maraknya konten negatif di media sosial. Konten negatif yang sering ditemui diantaranya isu suku, agama, ras, dan antargolongan (SARA), cyberbullying, serta body shamming, yang biasanya muncul disertai kalimat-kalimat umpatan. Hal tersebut menjadi sulit untuk diatasi karena jumlah pengguna internet di Indonesia yang sangat besar, sehingga perlu adanya sebuah sistem yang dapat mendeteksinya secara otomatis. Penelitian ini mengusulkan sistem dengan model Neural Network untuk deteksi konten negatif di media sosial dengan cara mempertimbangkan konteks kalimat atau frasa, tidak hanya kata-per-kata. Ada dua model NN yang dianalisis di penelitian ini, yaitu Artificial Neural Network (ANN) dan Recurrent Neural Network (RNN). Model RNN menunjukkan performa yang lebih baik dibandingkan dengan model ANN dengan akurasi training, validasi, dan test masing-masing adalah 94%, 84%, dan 84%.

No abstract

Health risk characteristics expressed as a Risk Quotient (RQ) can be carried out through an environmental health risk analysis (ARKL) approach. This approach can estimate the public health risk caused by the concentration of risk agents of particulates consisting of PM2.5, PM10, and TSP. The research on the fluctuation of ambient air particulate pollutant and its risk to public health was conducted in each sub-district of Bogor City. Author identified a total of 360 respondents to determine the community anthropometric variable of exposures for time, frequency, and duration. There are several steps that need to be carried out to obtain the RQ value, namely identification of hazards from particulate risk agents, analysis of the dose-response in the form of Reference Concentration (RFC), analysis of the exposure obtained based on anthropometric variables, and the concentration of risk agents as well as characteristics of risk levels. The risk level characteristic shows that the RQ value of TSP is always the highest one, followed by PM10 and PM2.5. The respective RQ values of TSP for male and female residents are 1.85 and 1.53. Cumulatively, the male and female population in Tanah Sareal produced the highest RQ values. Those are 4.44 and 3.36, respectively. At the same time, the lowest cumulative RQ was obtained for male and female residents in East Bogor with RQ values of 2.96 and 2.54. The RQ value of each risk agent or the cumulative RQ that is more than 1 (RQ> 1) is stated to have or has a health risk, so it needs to be controlled, while the RQ value which is less than one (1) is displayed not to need to be controlled but needs to be maintained. Keywords: particulate, risk level, exposure assessment, anthropometric characteristic, environmental health risk assessment   ABSTRAK Karakteristik risiko kesehatan yang dinyatakan sebagai Risk Quotient (RQ) dapat dilakukan melalui pendekatan Analisis Risiko Kesehatan Lingkungan (ARKL). Pendekatan ini dapat mengestimasi risiko kesehatan masyarakat yang disebabkan oleh konsentrasi agen risiko yaitu PM2,5, PM10, dan TSP di tiap-tiap kecamatan di Kota Bogor. Penulis mengidentifikasi sebanyak 360 responden yang terdiri dari laki-laki dan perempuan untuk menentukan variabel antropometri masyarakat di Kota Bogor, waktu paparan, frekuensi paparan, serta durasi paparan. Ada beberapa tahapan yang perlu dilakukan untuk memperoleh nilai RQ, yaitu identifikasi bahaya dari agen risiko partikulat, analisis dosis-respon berupa Reference Concentration (RfC), analisis pajanan yang diperoleh berdasarkan variabel antropometri dan konsentrasi agen risiko serta karakteristik tingkat risiko. Karakteristik tingkat risiko menunjukkan nilai RQ TSP selalu paling tinggi diikuti PM10, dan terendah adalah RQ PM2,5 dengan nilai tertinggi TSP untuk penduduk laki-laki dan perempuan masing-masing sebesar 1,85 dan 1,53. Secara kumulatif, penduduk laki-laki dan perempuan di Tanah Sareal menghasilkan nilai RQ tertinggi masing-masing sebesar 4,44 dan 3,36. Sedangkan RQ kumulatif terendah diperoleh untuk penduduk laki-laki dan perempuan di Bogor Timur dengan nilai RQ 2,96 dan 2,54. Nilai RQ tiap agen risiko ataupun RQ kumulatif yang lebih dari 1 (RQ>1) dinyatakan memiliki atau terdapat risiko kesehatan sehingga perlu dikendalikan, sementara nilai RQ yang masing kurang dari satu dinyatakan tidak perlu dikendalikan tetapi perlu dipertahankan. Kata kunci: partikulat, tingkat risiko, analisis pajanan, karakteristik antropometri, analisis risiko kesehatan lingkungan