IMPLEMENTASI ALGORITMA MULTINOMIAL NAIVE BAYES CLASSIFIER PADA SISTEM KLASIFIKASI SURAT KELUAR (Studi Kasus : DISKOMINFO Kabupaten Tangerang)

Kalokasari, Dea Herwinda; Shofi, Imam Marzuki; Setyaningrum, Anif Hanifa

doi:10.15408/jti.v10i2.6199

Cited by 9 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Multinomial Naive Bayes do better performance in 9 out of 13 models that [5] have. According to research from [6], the Multinomial Naïve Bayes algorithm has 89.58% accuracy in the letter classification system.…”

Section: Related Workmentioning

confidence: 99%

“…TF or Term-Frequency states how many words appear in a document. Meanwhile, IDF or Inverse Document Frequency states the number of documents that contain a word in one publication segment [6].…”

Section: Tf-idfmentioning

confidence: 99%

“…Parameter P(tk | c) (probability likelihood) is estimated by calculating the occurrence of tk on all training documents in c, using laplacean prior as shown in (6) [6]:…”

Section: E Multinomial Naive Bayesmentioning

confidence: 99%

“…Where Nk counts the total occurrence of tk in c's training document and N is the total occurrence of words in c [6]. For example, given training this training data:…”

Section: E Multinomial Naive Bayesmentioning

confidence: 99%

See 3 more Smart Citations

Spam Filtering On User Feedback Via Text Classification Using Multinomial Naïve Bayes And TF-IDF

Sadid¹,

Young²,

Rusli³

2022

Ultimatics

View full text Add to dashboard Cite

User feedback could give developer an information on what should be fixed or should be improved. But there are many user feedback that are actually spam. In user feedback, spam contents are more likely to be an inappropriate feedback, a feedback that is not actually a feedback, just some random comment or even a question. Reading and choosing feedback manually could be costly, especially in terms of time and energy. Therefore, this research focuses in building a spam filtering model using Multinomial Naïve Bayes that implement a TF/IDF approach to detect spam automatically. For text classification, Multinomial Naïve Bayes proved on having better speed and having good performance. With TF/IDF, word that highly occurred in many documents has less impact than other so it could help increasing performance from imbalanced dataset. This research aims to implement Multinomial Naïve Bayes for spam filtering in user feedback and to measure performance of the model. Best performance of this classifier was obtained when using up-sampling method and typo corrector with 70:30 ratio of train and test set resulting in 89.25% for accuracy, 45% for precision, 56% for recall, and 50% for F1-Score.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Tf-idfmentioning

confidence: 99%

“…Parameter P(tk | c) (probability likelihood) is estimated by calculating the occurrence of tk on all training documents in c, using laplacean prior as shown in (6) [6]:…”

Section: E Multinomial Naive Bayesmentioning

confidence: 99%

“…Where Nk counts the total occurrence of tk in c's training document and N is the total occurrence of words in c [6]. For example, given training this training data:…”

Section: E Multinomial Naive Bayesmentioning

confidence: 99%

See 2 more Smart Citations

Spam Filtering On User Feedback Via Text Classification Using Multinomial Naïve Bayes And TF-IDF

Sadid¹,

Young²,

Rusli³

2022

Ultimatics

View full text Add to dashboard Cite

show abstract

“…Selanjutnya, metode Naïve Bayes yang digunakan untuk membangun model klasifikasi pada penelitian ini adalah Multinomial Naïve Bayes. Metode Multinomial Naïve Bayes dipilih dengan alasan bahwa algoritma tersebut cocok diterapkan untuk klasifikasi teks atau dokumen [10]. Sedangkan untuk membangun model klasifikasi dengan algoritma SVM, dilakukan dengan pendekatan linear kernel.…”

Section: A Pengumpulan Dataunclassified

Untitled

Hidayatullah¹,

Fadila²,

Juwairi³

et al. 2019

JLK

View full text Add to dashboard Cite

Penelitian ini bertujuan untuk melakukan identifikasi tweet yang mengandung konten kasar atau ofensif. Untuk melakukan hal tersebut, ada lima tahap yang dilalui yaitu pengumpulan data, preprocessing, ekstraksi fitur, klasifikasi, dan evaluasi. Adapun algoritma klasifikasi yang digunakan adalah Multinomial Naïve Bayes dan Support Vector Machine dengan linear kernel. Berdasarkan eksperimen, diketahui bahwa performa algoritma Support Vector Machine dengan linear kernel lebih unggul secara keseluruhan dibandingkan dengan algoritma Multinomial Naïve Bayes. Hal tersebut dilihat dari perolehan nilai accuracy, precision, recall, dan F1-score untuk algoritma SVM berturut-turut adalah 0.9928; 0.9914; 0.9946; dan 0.9930. Sedangkan perolehan accuracy, precision, recall, dan F1-score algoritma Multinomial Naïve Bayes berturut-turut adalah 0.9834; 0.9912; 0.9762; dan 0.9836. Namun demikian, dapat disimpulkan bahwa algoritma Support Vector Machine dan Multinomial Naïve Bayes memiliki performa yang hampir sama baiknya. Hal tersebut dibuktikan dengan selisih capaian performa yang tidak terlalu mencolok dari keduanya.

show abstract

Python Based Machine Learning Text Classification

Mujilahwati

Sholihin

Wardhani

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Machine learning is a clear indication that technological progress is accelerating right now. All jobs must be done instantly and quickly in the digital world, making businessmen more competitive. There is also a pressing demand for machine learning in education. As far as future policies go, this is relevant. Included in this issue is the challenge of evaluating the substance of a student’s thesis abstract for accuracy, appropriateness, and topicality. One method for addressing these issues is classification. The appropriateness level of abstract writing can be determined by classifying the labeled training data according to the topic. Of course, the training and test data will be cleaned or pre-processed prior to classification. Pre-processing and classification tasks benefit from the python library’s speed and accuracy. In 2019, 126 abstract papers with 8 labels were used, and in 2020, 116 abstract documents with 8 labels were used. The student’s thesis abstract follows the topic with an accuracy of 93.85 percent, a precision of 97 percent, and a recall of 95 percent, according to the results of the study.

show abstract

IMPLEMENTASI ALGORITMA MULTINOMIAL NAIVE BAYES CLASSIFIER PADA SISTEM KLASIFIKASI SURAT KELUAR (Studi Kasus : DISKOMINFO Kabupaten Tangerang)

Cited by 9 publications

References 1 publication

Spam Filtering On User Feedback Via Text Classification Using Multinomial Naïve Bayes And TF-IDF

Spam Filtering On User Feedback Via Text Classification Using Multinomial Naïve Bayes And TF-IDF

Untitled

Python Based Machine Learning Text Classification

Contact Info

Product

Resources

About