Rating Of Indonesian sinetron based on public opinion in Twitter using Cosine similarity

Prasetyo, Vincentius Riandaru; Winarko, Edi

doi:10.1109/icstc.2016.7877374

Cited by 11 publications

(16 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Also, three more researchers have used Twitter data for predicting television (TV) ratings. D'Souza et al (2013) have worked on Indian TV ratings, Akarsu and Diri (2016) have worked on Turkish TV ratings and Prasetyo and Winarko (2016) have worked on an Indonesian TV program rating. Prasetyo and Winarko (2016) have used a combination of cosine-based similarity and term frequency–inverse document frequency (TF–IDF).…”

Section: Literature Reviewmentioning

confidence: 99%

“…D'Souza et al (2013) have worked on Indian TV ratings, Akarsu and Diri (2016) have worked on Turkish TV ratings and Prasetyo and Winarko (2016) have worked on an Indonesian TV program rating. Prasetyo and Winarko (2016) have used a combination of cosine-based similarity and term frequency–inverse document frequency (TF–IDF). This combination revealed better accuracy for similarity calculations.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Utilizing emotion scores for improving classifier performance for predicting customer's intended ratings from social media posts

Ray

Bala

Jain³

2020

BIJ

View full text Add to dashboard Cite

PurposeSocial media channels provide an avenue for expressing views about different services/products. However, unlike merchandise/company websites (where users can post both reviews and ratings), it is not possible to understand user's ratings for a particular service-related comment on social media unless explicitly mentioned. Predicting ratings can be beneficial for service providers and prospective customers. Additionally, predicting ratings from a user-generated content can help in developing vast data sets for recommender systems utilizing recent data. The aim of this study is to predict ratings more accurately and enhance the performance of sentiment-based predictors by combining it with the emotional content of textual data.Design/methodology/approachThis study had utilized a combination of sentiment and emotion scores to predict the ratings of Twitter posts (3,509 tweets) in three different contexts, namely, online food delivery (OFD) services, online travel agencies (OTAs) and online learning (e-learning). A total of 29,551 reviews were utilized for training and testing purposes.FindingsResults of this study indicate accuracies of 58.34%, 57.84% and 100% in cases of e-learning, OTA and OFD services, respectively. The combination of sentiment and emotion scores showed an increase in accuracies of 19.41%, 27.83% and 40.20% in cases of e-learning, OFD and OTA services, respectively.Practical implicationsUnderstanding the ratings of social media comments can help both service providers as well as prospective customers who do not spend much time reading posts but want to understand the perspectives of others about a particular service/product. Additionally, predicting ratings of social media comments will help to build databases for recommender systems in different contexts.Originality/valueThe uniqueness of this study is in utilizing a combination of sentiment and emotion scores to predict the ratings of tweets related to different online services, namely, e-learning OFD and OTAs.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Utilizing emotion scores for improving classifier performance for predicting customer's intended ratings from social media posts

Ray

Bala

Jain³

2020

BIJ

View full text Add to dashboard Cite

show abstract

“…Salah satu algoritma yang dapat digunakan untuk proses stemming dari teks berbahasa Indonesia adalah Nazief Andriani. Stemming memiliki 2 tahapan utama yaitu pengecekan kata dasar dan penghapusan afiks, prefiks, dan sufiks pada suatu kata [11]. Apabila hasil penghapusan stopword pada Tabel 1 dilakukan proses stemming, maka hasilnya ditunjukkan pada Tabel 2.…”

Section: B2 Stemmingunclassified

Penentuan Pembimbing Tugas Akhir Mahasiswa Jurusan Teknik Informatika Universitas Surabaya Dengan Metode Dice Coefficient

Prasetyo

Hartanto

Mulyono

2019

teknika

Self Cite

View full text Add to dashboard Cite

Tugas Akhir (TA) adalah sebuah karya ilmiah yang harus dibuat oleh mahasiswa jurusan Teknik Informatika, Universitas Surabaya sebagai salah satu syarat kelulusan. Dalam mengajukan topik TA, mahasiswa wajib membuat dan mengumpulkan proposal TA tersebut. Setelah itu, ketua jurusan akan menentukan calon dosen pembimbing, dosen reviewer 1, dan dosen reviewer 2 sesuai dengan kompetensi untuk proposal tersebut. Dalam proses pengajuan proposal tersebut, terdapat beberapa masalah yang muncul, yakni adanya kemungkinan kesalahan penentuan pembimbing karena proses penentuannya berdasarkan pengetahuan pribadi dari ketua jurusan, kesulitan memantau perkembangan proses pengajuan proposal, dan kesulitan untuk melakukan pemerataan pembimbing TA. Untuk mengatasi masalah tersebut, dibuatlah sistem untuk melayani administrasi pengajuan topik TA beserta penentuan pembimbing. Proses penentuan pembimbing akan menggunakan metode Dice Coefficient. Dari hasil pengujian sistem dengan metode K-Fold Cross Validation dengan nilai k = 100 untuk 1000 data TA yang ada, didapatkan nilai akurasi sistem sebesar 36,25%. Apabila diambil 100 data TA yang memiliki dosen pembimbing yang ideal, sistem memberikan nilai akurasi yang lebih baik yaitu sebesar 45,5%.

show abstract

“…This step is a process to find the root of a word that will be implemented with Nazief Andriani algorithm (Sastrawi 1.0.1). The process of stemming consists of two main phase, ie: checking of the basic word and elimination of affixes, prefixes, suffixes [12].…”

Section: Stemmingmentioning

confidence: 99%

“…Term extraction aims to eliminate the duplication of words contained in the preprocessing results so that will be obtained a set of unique words [12]. Term weighting will be calculated using term frequency and TF-IDF.…”

Section: Term Extraction and Term Weightingmentioning

confidence: 99%

Searching Cheapest Product on Three Different E-Commerce Using K-Means Algorithm

Prasetyo

2018

2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)

Self Cite

View full text Add to dashboard Cite

The development of e-commerce is starting to change people's lifestyles, not least the people of Indonesia. The existence of e-commerce is very helpful user in buying and selling products. There are many e-commerce that can be found today. Some of the famous e-commerce in Indonesia are Bukalapak, Lazada, and Blibli. A large number of existing ecommerce makes users, especially buyers, have difficulty when looking for products at the cheapest price. This happens because each e-commerce offers different prices for the same product. This research aims to make the cheapest product search system in Bukalapak, Lazada, and Blibli using K-Means algorithm. The results of experiments showed that K-Means algorithm can be used to classify product data from Bukalapak, Lazada, and Blibli well. The results of the clustering process can also help for searching the cheapest products from the three e-commerce becomes faster. However, the number of clusters used will affect the effectiveness of the search process on the system.

show abstract

Rating Of Indonesian sinetron based on public opinion in Twitter using Cosine similarity

Cited by 11 publications

References 1 publication

Utilizing emotion scores for improving classifier performance for predicting customer's intended ratings from social media posts

Utilizing emotion scores for improving classifier performance for predicting customer's intended ratings from social media posts

Penentuan Pembimbing Tugas Akhir Mahasiswa Jurusan Teknik Informatika Universitas Surabaya Dengan Metode Dice Coefficient

Searching Cheapest Product on Three Different E-Commerce Using K-Means Algorithm

Contact Info

Product

Resources

About