Application of recommendation system  with AHP method and sentiment analysis

Prasetyaningrum, Ira; Fathoni, Kholid; Priyantoro, Tri Tangguh Jiwo

doi:10.12928/telkomnika.v18i3.14778

Cited by 11 publications

(7 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Stemming adalah proses untuk meniadakan imbuhan yang didapati pada suatu kata menjadi sebuah kata dasar (Prasetyaningrum et al, 2020). Proses ini memiliki tujuan untuk mengurangi banyaknya varians dari suatu kata agar tidak menambah beban memori.…”

Section: Stemmingunclassified

Analisis Sentimen Tweet Tentang UU Cipta Kerja Menggunakan Algoritma SVM Berbasis PSO

Sabrila

Azhar

Aditya

2022

JISKa

View full text Add to dashboard Cite

Support Vector Machine (SVM) is one of the most widely used classification algorithms for sentiment analysis and has been shown to provide satisfactory performance. However, despite its advantages, the SVM algorithm still has weaknesses in selecting the right SVM parameters to optimize the performance. In this study, sentiment analysis was done with the use of data called tweets about Undang-Undang Cipta Kerja which reap many pros and cons by the people in Indonesia, especially the laborers. The classification method used in this study is the Support Vector Machine algorithm which is optimized using the Particle Swarm Optimization method for the SVM parameters selection in the hope of optimizing the performance generated by the SVM algorithm in sentiment analysis. The results of the study using 10 k-fold cross-validations using the SVM algorithm resulted in an accuracy of 92,99%, a precision of 93,24%, and a recall of 93%. Meanwhile, the SVM and PSO algorithms produce an accuracy of 95%, precision of 95,08%, and recall of 94,97%. The results show that the Particle Swarm Optimization method can overcome the weaknesses of the Support Vector Machine algorithm in the problem of parameter selection and has succeeded in improving the resulting performance where the SVM-PSO is more superior to SVM without optimization in sentiment analysis.

show abstract

Section: Stemmingunclassified

Analisis Sentimen Tweet Tentang UU Cipta Kerja Menggunakan Algoritma SVM Berbasis PSO

Sabrila

Azhar

Aditya

2022

JISKa

View full text Add to dashboard Cite

show abstract

“…Determination of KIP Recipients using the Moora method at SD Negeri 124395 Pematang Siantar (Sinaga & Andani, 2018). Application of a recommendation system using the AHP method and sentiment analysis (Prasetyaningrum et al, 2020). Decision Support System for Student PKL Place Selection Groups Using AHP and Borda Methods (Nur Ilham & Mulyana, 2017).…”

Section: Literature Reviewmentioning

confidence: 99%

Application of the AHP Method for KIP Recommendation Applications -College Students

Satria¹,

Ilham²,

Budiansyah

et al. 2021

CNAHPC

View full text Add to dashboard Cite

The Smart Indonesia Card (KIP) is an assistance in the form of cash from the government given to students whose parents are less able to finance their education, as a continuation and expansion of the targets of the Poor Student Assistance (BSM) program. KIP has a goal, namely to increase access for children aged 6 (six) to 21 (twenty-one years) to obtain educational services until they graduate from high school to support the implementation of Universal Secondary Education / Pilot Compulsory Education 12 (twelve) years, prevent students from the possibility of dropping out of school or not continuing their education due to economic difficulties. The KIP-Kuliah, formerly known as Bidikmisi, is presently in service. They may find it difficult to determine who is a qualified candidate to become a recommendation for KIP-Kuliah recipients who will be presented to the system since many variables and assessments will be passed in determining the prospective KIP-Kuliah recipients. Therefore, from this problem, a system is needed that can quickly and accurately assess the eligibility of KIP-Lecture recipients without having to sort out the files that have been collected one by one. As a result, it is deemed necessary to develop a decision-making system to address the existing issues. The steps of research that will be carried out to create a decision support system will collect criteria and sub-criteria from the assessment and then enter them into the calculation formula or method employed, namely the AHP method.

show abstract

“…where 𝛾 is the learning rate, which is a constant value that controls the regularization error during the training stage. After optimizing the values of the vectors, prediction values are computed using as shown in (3). Finally, the evaluation process is performed to compute the accuracy of the prediction by comparing the results of the proposed method with the testing part through the mean absolute error (MAE) and root mean square error (RMSE).…”

Section: 𝑝𝑟𝑜(𝑥 𝑦mentioning

confidence: 99%

“…Therefore, a recommendation system is utilized to solve the aforementioned problem by reducing search times and predicting a user's preferences of products. A recommendation system (RS) can be defined as a tool that can recommend a list of items to interested users [3]. A recommendation system comes in a variety of types, collaborative filtering being the most common and most widely used [4,5].…”

Section: Introductionmentioning

confidence: 99%

Adopting explicit and implicit social relations by SVD++ for recommendation system improvement

2021

View full text Add to dashboard Cite

Recommender systems suffer a set of drawbacks such as sparsity. Social relations provide a useful source to overcome the sparsity problem. Previous studies have utilized social relations or rating feedback sources. However, they ignored integrating these sources. In this paper, the limitations of previous studies are overcome by exploiting four sources of information, namely: explicit social relationships, implicit social relationships, users' ratings, and implicit feedback information. Firstly, implicit social relationships are extracted through the source allocation index algorithm to establish new relations among users. Secondly, the similarity method is applied to find the similarity between each pair of users who have explicit or implicit social relations. Then, users' ratings and implicit rating feedback sources are extracted via a user-item matrix. Furthermore, all sources are integrated into the singular value decomposition plus (SVD++) method. Finally, missing predictions are computed. The proposed method is implemented on three realworld datasets: Last.Fm, FilmTrust, and Ciao. Experimental results reveal that the proposed model is superior to other studies such as SVD, SVD++, EU-SVD++, SocReg, and EISR in terms of accuracy, where the improvement of the proposed method is about 0.03% for MAE and 0.01% for RMSE when dimension value (d) = 10.

show abstract

Application of recommendation system with AHP method and sentiment analysis

Cited by 11 publications

References 2 publications

Analisis Sentimen Tweet Tentang UU Cipta Kerja Menggunakan Algoritma SVM Berbasis PSO

Analisis Sentimen Tweet Tentang UU Cipta Kerja Menggunakan Algoritma SVM Berbasis PSO

Application of the AHP Method for KIP Recommendation Applications -College Students

Adopting explicit and implicit social relations by SVD++ for recommendation system improvement

Contact Info

Product

Resources

About