Ilmi, Rifqy Rosyidah (2024) Model analisis prediksi rating film menggunakan Random Forest dan Neural Network. Masters thesis, Universitas Islam Negeri Maulana Malik Ibrahim.
This is the latest version of this item.
Text (Fulltext)
200605220003.pdf - Accepted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (10MB) |
Abstract
ABSTRAK
Rating film menjadi salah satu indikator utama kesuksesan suatu film. Rating film tidak hanya mencerminkan preferensi penonton, tetapi juga memiliki dampak signifikan terhadap pendapatan dan popularitas film. Penelitian ini bertujuan mengidentifikasi faktor-faktor yang mempengaruhi rating film pada situs IMDb, serta membandingkan performa metode klasifikasi Random Forest (RF) dan Neural Network (NN) dalam memprediksi rating film. Analisis menunjukkan bahwa genre Drama, Drama/Romance, dan Action/Crime/Thriller, serta tema judul yang mencerminkan pengalaman universal seperti "Love" dan "Life," memiliki korelasi positif dengan skor IMDb. Film berdurasi panjang dan dengan rating dewasa juga cenderung lebih dihargai oleh audiens. Dalam perbandingan model, RF menunjukkan performa paling optimal. Pada skenario dengan penerapan SMOTE, akurasi RF mencapai 0.78 dengan nilai presisi dan recall yang konsisten dalam mendeteksi kelas positif pada data yang tidak seimbang. Model NN menunjukkan performa yang lebih fluktuatif dan membutuhkan penyesuaian lebih lanjut.
ABSTRACT
Film ratings are one of the key indicators of a film's success. Film ratings not only reflect audience preferences but also have a significant impact on the film's revenue andpopularity. This study aims to identify the factors influencing film ratings on IMDb and compare the performance of the Random Forest (RF) and Neural Network (NN) classification methods in predicting film ratings. The analysis shows that genres such as Drama, Drama/Romance, and Action/Crime/Thriller, as well as titles with universal themes like "Love" and "Life," are positively correlated with IMDb scores. Films with longerdurations and adult ratings also tend to be rated higher by audiences. In the modelcomparison, RF demonstrated the most optimal performance. In the skenario usingSMOTE, RF achieved an accuracy of 0.78 with consistent precision and recall values indetecting the positive class in imbalanced data. The NN model showed more fluctuatingperformance and requires further adjustments.
مستخلص البحث
ت تامييقت ملافلأا نم زربأ تارشؤم حانج مليفلا . ثيح لا سكعت تامييقت ملافلأا تلايضفت روهملجا ،طقف لب اله أي ًضا يرث Äيربكةنراقمو ءادأ IMDbىلع تاداريإ مليفلا هتيبعشو . فد Ñهذه ةساردلا لىإ ديدتح لماوعلا تيلا رثؤت في تامييقت ملافلأا ىلع عقومفي ؤبنتلا تامييقتب ملافلأا . ترهظأ تلايلحتلا نأ عاونلأا ) (NNةكبشلاو ةيبصعلا ) (RFبيلاسأ فينصتلا لثم ةباغلا ةيئاوشعلا،" لثم ،اماردلا اماردلا / ،ةيسنامورلا نشكلأاو / ةيمرلجا / ،قيوشتلا كلذكو نيوانعلا تيلا يوتتح ىلع عيضاوم ةيلماع لثم " بلحا "و " ةايلحاامك نأ ملافلأا تاذ ةدلما ةليوطلا فينصتلاو يرمعلا رابكلل ليتم أي ًضا لىإ لوصلحا ىلع . IMDbطبترت ارتباطًا إيجابيًا عم تاجردتامييقت ىلعأ نم روهملجا .في ةنراقم ،جذامنلا ترهظأ ةباغلا ةيئاوشعلا أداءً رثكأ ةءافك .في ويرانيسلا يذلا تم هيف مادختساتققح ةباغلا ةيئاوشعلا ةقد لصت لىإ 0.78عم ميق ةتب ùـلل " ةقد "و" عاجترسلاا "في فشكلا نع ةئفلا ةيبايجلإا في ،SMOTE. تZايبلا يرغ ةنزاوتلما . امنيب ترهظأ ةكبشلا ةيبصعلا أداءً رثكأ تقلبًا جاتتحو لىإ ديزم نم تلايدعتل
Item Type: | Thesis (Masters) |
---|---|
Supervisor: | Kurniawan, Fachrul and Yaqin, M. Ainul |
Keywords: | IMDb; Random Forest; Neural Network; SMOTE; الكلمات المفتاحية; IMDb ; الغابة العشوائية،;الشبكة العصبية ;SMOTE. |
Subjects: | 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080105 Expert Systems 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080110 Simulation and Modelling 08 INFORMATION AND COMPUTING SCIENCES > 0802 Computation Theory and Mathematics > 080201 Analysis of Algorithms and Complexity |
Departement: | Fakultas Sains dan Teknologi > Jurusan Magister Tehnik Informatika |
Depositing User: | RIFQY ROSYIDAH ILMI |
Date Deposited: | 08 Jan 2025 11:02 |
Last Modified: | 08 Jan 2025 11:02 |
URI: | http://etheses.uin-malang.ac.id/id/eprint/72280 |
Downloads
Downloads per month over past year
Available Versions of this Item
-
Model analisis prediksi rating film menggunakan Random Forest dan Neural Network. (deposited UNSPECIFIED)
- Model analisis prediksi rating film menggunakan Random Forest dan Neural Network. (deposited 08 Jan 2025 11:02) [Currently Displayed]
Actions (login required)
View Item |