Supervised learning methods application to sentiment analysis

Altares-López, Sergio; Cuadrado-Gallego, Juan J.

doi:10.1145/3331076.3331086

Cited by 5 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Saat ini Artificial Intelligence AI (kecerdasan buatan) terus berkembang dan telah banyak peneliti yang memanfaatkannya guna memecahkan masalah-masalah yang ada di dunia. Salah satu cabang ilmu dari AI tersebut adalah Natural Language Processing (NLP) (Sergio & Juan J, 2019). Salah satu penerapan NLP yang cukup terkenal adalah Sentiment Analysis (analisis sentimen) (S. Fouzia, Nagaratna, Hegde, & Khaleel, 2018).…”

Section: Pendahuluanunclassified

“…Seperti yang telah dijelaskan sebelumnya, komputer tidak mampu memahami ekspresi manusia pada teks secara langsung layaknya manusia, disini dibutuhkan metode untuk mengubah data teks tersebut menjadi kumpulan angka atau vector yang biasa disebut vectorization (Sergio & Juan J, 2019). Ada beberapa metode ekstraksi fitur yang telah banyak digunakan, seperti yang sangat terkenal TF-IDF (Term Frequency-Inverse Document Frequency) yaitu pembobotan suatu kata pada sebuah dokumen.…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Averaged Word2vec sebagai Ekstraksi Fitur pada Analisis Sentimen Ulasan Film di IMDb menggunakan Artificial Neural Network (ANN)

Darwis Alwan,

Ridla

2024

JUSTINDO

View full text Add to dashboard Cite

Analisis Sentimen sangat dibutuhkan saat ini, dengan kemajuan dan peningkatan penggunaan internet saat ini orang dapat dengan mudah mengungkapkan pendapatnya melalui internet (online). Salah satu situs paling populer yang dapat digunakan orang untuk mengungkapkan komentarnya adalah IMDb (Internet Movie Database), situs resmi untuk database informasi terkait film dan acara tv. Ada jutaan review orang untuk banyak film di situs IMDb. Pengguna IMDb semakin meningkat dari hari ke hari sehingga komentar terhadap film juga meningkat di situs tersebut. Untuk mengetahui jumlah reaksi positif dan negatif dengan mudah, maka perlu adanya analisis sentimen pada tinjauan data. Pada penelitian analisis sentimen ini, metode ekstraksi ciri yang digunakan adalah rata-rata Word2Vec. Word2Vec adalah teknik penyisipan kata yang dapat menangkap makna semantik kata. Untuk melengkapi proses analisis sentimen penelitian ini menggunakan metode ANN (Artificial Neural Network) sebagai pengklasifikasi. Berdasarkan hasil uji coba dengan dataset review film IMDb, metode yang diusulkan mampu mencapai akurasi sebesar 88,52%. Hasil ini membuktikan bahwa metode yang diusulkan mampu mengklasifikasikan sentimen ulasan film dan juga metode yang diusulkan ini merupakan klasifikasi yang sangat baik dengan luas area di bawah kurva (AUC) sebesar 95%. Selain itu, metode Word2Vec rata-rata memiliki akurasi yang lebih tinggi daripada metode berbasis frekuensi istilah, BOW dan TF-IDF.

show abstract

Section: Pendahuluanunclassified

Averaged Word2vec sebagai Ekstraksi Fitur pada Analisis Sentimen Ulasan Film di IMDb menggunakan Artificial Neural Network (ANN)

Darwis Alwan,

Ridla

2024

JUSTINDO

View full text Add to dashboard Cite

show abstract

“…Despite having five emotional word dictionaries and WordNet when evaluating emotions, inconsistencies occur in which evaluations are divided, making it an NP‐complete problem. López and Cuadrado‐Gallego (2019) compared the use of various supervised learning methods for sentiment analysis. They found that TF‐IDF, which is a method for evaluating the importance of words, is often used in sentiment analysis.…”

Section: Related Workmentioning

confidence: 99%

Measurement and quantification of an individual's feelings for a place in personal data analysis

Kasuya

Tago

Jin

2021

Human Behav and Emerg Tech

View full text Add to dashboard Cite

Location‐related data are an important subset of personal data. An individual may have a positive or negative feeling for a specific place, which is important for personal data analysis. There are many studies on sentiment analysis within text data, such as tweets, but few studies have been conducted specifically on an individual's feelings regarding locations. In this study, we focus on measuring and quantifying an individual's feelings for a place using three representative methods in sentiment analysis: emotion dictionary, personalized dictionary, and Bayesian classification. We design an experiment to evaluate these methods using tweet data including locations and an individual's emotional changes with regard to these locations before entering, after exiting, and in a location. Three sets of emotion scores are obtained and normalized. Furthermore, we set four protocols and use statistical methods to compare these emotion scores with the subjective emotion scores provided by the user whose tweets are used in the experiment. Experimental results show that Bayesian classification performs the best in measuring and quantifying an individual's feelings for a place.

show abstract

“…MES timestamps, product measurement, telemetric data of equipment), whereas SA uses subjective data gathered directly from humans. López and Cuadrado-Gallego (2008) stated that SA is an application of natural language processing that belongs to the area of artificial intelligence. This type of classification is reasonable and supports the idea of separating the raw-data-based approaches in data analytics from SA and text mining due to substantial differences of methods, input data and areas of application.…”

Section: Definition and Overview Of Predictive Analyticsmentioning

confidence: 99%

Analysis and Evaluation of the Impacts of Predictive Analytics on Production System Performances in the Semiconductor Industry.

Preis¹

View full text Add to dashboard Cite

Problem Statement: Predictive Analytics (PA) may effectively support semiconductor industry (SI) companies in order to manage the special challenges in SI value chains. To discover the implications of PA, the realistic benefits as well as its limitations of its application to semiconductor manufacturing, it is necessary to assess in which ways the application of PA affects the production system (PS) performances. However, based on the literature survey, the influences of PA on the various performance characteristics of an SI PS are not as clear as expected for the efficiently operative application. Besides, the existing performance models are not effective to predict the impacts of PA on the SI PS performances. Therefore, the overall aim of this thesis is to analyse and evaluate the impacts of PA on the SI PS performances and to identify under which conditions a PA application would generate the most significant performance improvements. The focus of this thesis is predictive maintenance (PdM). Research Methodology: Based on a post-positivist philosophy, the thesis applies a deductive research approach using mixed-methods for data collection. The research design has the following stages: (1) theory, (2) hypothesis, (3) state of research, (4) case study and (5) verification. Main Achievements: (1) The systematic literature review is carried out to identify the gaps of the existing research and based on these findings, a conceptual framework is proposed and developed. (2) The existing performance models are analysed and evaluated against their applicability to this study. (3) A causal loop model for SI PS is generated based on the assessment of experts with industrial engineering and equipment maintenance expertise. (4) An expert system is developed and evaluated in order to investigate transitive and contradictory effects of PdM on SI PS performances. (5) A simulation model is developed and validated for investigating the strengths and limitations of PdM regarding SI PS performances under different circumstances. Results: The results of the logical inference study show that PdM has 34 positive effects as well as 4 contradictory effects on SI PS performance characteristics. Based on the various simulation experiments, it has been found that (1) ’Mean Time to Repair’ decreases only if PdM supports proportionate reduction of failures and repair times. (2) Logistics performance improves only if the underlying workcenter is limited in capacity or the four partners are nonsynchronous. (3) PdM supports optimal cost decreases for workcenters where the degree of exhausting wear limits can be most effectively improved and (4) the degree of yield improvement gained by PdM is dependent on the operation scrap rate. However, (5) if a workcenter has overcapacity, PdM will potentially worsen PS performances, even if the particular workcenter performance can be improved. These new insights advance existing knowledge in production managements when adopting predictive technologies at SI PS in order to improve PS performances. The findings above enable SI practitioners to justify a PdM investment and to select suitable workcenters in order to improve SI PS performances by applying the proposed PdM. Contributions: The main contributions of this PhD project can be divided into practical application and theoretical work. The contributions from the theoretical perspective are: 1) The critical review and evaluation of the state of the research for PA in the context of semiconductor manufacturing and the models for predicting and evaluating SI PS performances. 2) A new framework for investigating the implications of PA on the challenges such as gaining high utilizations and controlling the variability in production processes in SI value chains. 3) The new knowledge about transitive and contradictory effects of PdM on SI PS performances, which indicates that PdM can be used to improve PS performances beyond a single machine. 4) The new knowledge about strengths and limitations of PdM in order to improve SI PS performances under particular circumstances. The contributions from the practical application perspective are: 1) A practical method for identifying workcenters where PdM delivers the most significant benefits for SI PS performances. 2) An expert system that provides a comprehensive knowledge base about causes and effects within SI PS in order to justify a PdM investment. 3) A concise review of important PA applications, their capabilities for the wafer fabrication and the most suited PA methods. These findings can be adopted by SI practitioners.

show abstract

Supervised learning methods application to sentiment analysis

Cited by 5 publications

References 14 publications

Averaged Word2vec sebagai Ekstraksi Fitur pada Analisis Sentimen Ulasan Film di IMDb menggunakan Artificial Neural Network (ANN)

Averaged Word2vec sebagai Ekstraksi Fitur pada Analisis Sentimen Ulasan Film di IMDb menggunakan Artificial Neural Network (ANN)

Measurement and quantification of an individual's feelings for a place in personal data analysis

Analysis and Evaluation of the Impacts of Predictive Analytics on Production System Performances in the Semiconductor Industry.

Contact Info

Product

Resources

About