Sentiment Analysis Based on Weighted Word2vec and Att-LSTM

Yuan, Huanhuan; Wang, Yongli; Xing, Feng; Sun, Shurong

doi:10.1145/3297156.3297228

Cited by 11 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Studies have also been conducted to reflect the frequency of occurrence of each element constituting a sequence [7], [8], [9]. This is typically used in natural language processing.…”

Section: Related Work a Prediction Using The Weight Of Sequence Datamentioning

confidence: 99%

“…This is typically used in natural language processing. Yuan et al [7] suggested giving term frequencyinverse document frequency (TF-IDF) weights based on the frequency of occurrence of words to textual emotion analysis and tried to learn by reflecting the importance of each word in the text. To classify whether sentences on simple notation services (SNS) are sarcasm identified, Onan [8] tested various weight functions to reflect the importance of each word in learning.…”

Section: Related Work a Prediction Using The Weight Of Sequence Datamentioning

confidence: 99%

See 1 more Smart Citation

Time-Weighted Cumulative LSTM Method Using Log Data for Predicting Credit Card Customer Turnover

Eom

Kim

2023

IEEE Access

View full text Add to dashboard Cite

One of the most important challenges for credit card companies is to retain customers. To achieve this, they predict whether customers will use credit cards and respond preemptively through marketing. Improper prediction leads to an increase in marketing costs; therefore, improving the performance of the prediction model is an important challenge for credit card companies. Therefore, credit card companies are working toward increasing the predictive power of the model, but the data used for learning are limited to formal data, such as card payment data; the log history stored on the application is not used. Prediction models using sequence data, such as log history, are being studied. However, no studies so far have appropriately utilized card payment data, log history, and information on the timing of the elements constituting the sequence. In this paper, we propose a method for predicting credit card turnover using application log and credit card payment data. The method embeds log data and weights each log using a term-weighting function. In addition, the time difference between the day customers visit the app and the last day of the month in which they leave is calculated. The weight value is higher when the timespan is shorter. The weighted log data were trained with a 2-layer LSTM model and its output layer was combined with the output layer trained with the card payment data for customer turnover prediction. It was verified that the model presented in this paper had a higher performance than the model using only card payment data and the model using only a time-weighted log sequence.INDEX TERMS Term-weighting, time weighted model, log analysis, predictive models.

show abstract

“…Studies have also been conducted to reflect the frequency of occurrence of each element constituting a sequence [7], [8], [9]. This is typically used in natural language processing.…”

Section: Related Work a Prediction Using The Weight Of Sequence Datamentioning

confidence: 99%

Section: Related Work a Prediction Using The Weight Of Sequence Datamentioning

confidence: 99%

Time-Weighted Cumulative LSTM Method Using Log Data for Predicting Credit Card Customer Turnover

Eom

Kim

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Klasifikasi teks dalam Natural Language Processing (NLP) sudah diterapkan pada aplikasi seperti indexing [10], ranking [11], sentiment analysis [12], retrieval information [13], dan klasifikasi dokumen [14]. Pelabelan dokumen baru sesuai dengan kategori yang benar, tergantung pada banyaknya dokumen berlabel yang ada untuk referensi [15].…”

Section: Pendahuluanunclassified

Komparasi Ekstraksi Fitur dalam Klasifikasi Teks Multilabel Menggunakan Algoritma Machine Learning

Efrizoni¹,

Defit

Tajuddin

et al. 2022

matrik

View full text Add to dashboard Cite

Ektraksi fitur dan algoritma klasifikasi teks merupakan bagian penting dari pekerjaan klasifikasi teks, yang memiliki dampak langsung pada efek klasifikasi teks. Algoritma machine learning tradisional seperti Na¨ıve Bayes, Support Vector Machines, Decision Tree, K-Nearest Neighbors, Random Forest, Logistic Regression telah berhasil dalam melakukan klasifikasi teks dengan ektraksi fitur i.e. Bag ofWord (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), Documents to Vector (Doc2Vec), Word to Vector (word2Vec). Namun, bagaimana menggunakan vektor kata untuk merepresentasikan teks pada klasifikasi teks menggunakan algoritma machine learning dengan lebih baik selalumenjadi poin yang sulit dalam pekerjaan Natural Language Processing saat ini. Makalah ini bertujuan untuk membandingkan kinerja dari ekstraksi fitur seperti BoW, TF-IDF, Doc2Vec dan Word2Vec dalam melakukan klasifikasi teks dengan menggunakan algoritma machine learning. Dataset yang digunakan sebanyak 1000 sample yang berasal dari tribunnews.com dengan split data 50:50, 70:30, 80:20 dan 90:10. Hasil dari percobaan menunjukkan bahwa algoritma Na¨ıve Bayes memiliki akurasi tertinggi dengan menggunakan ekstraksi fitur TF-IDF sebesar 87% dan BoW sebesar 83%. Untuk ekstraksi fitur Doc2Vec, akurasi tertinggi pada algoritma SVM sebesar 81%. Sedangkan ekstraksi fitur Word2Vec dengan algoritma machine learning (i.e. i.e. Na¨ıve Bayes, Support Vector Machines, Decision Tree, K-Nearest Neighbors, Random Forest, Logistic Regression) memiliki akurasi model dibawah 50%. Hal ini menyatakan, bahwa Word2Vec kurang optimal digunakan bersama algoritma machine learning, khususnya pada dataset tribunnews.com.

show abstract

“…Text classification is an important part of Natural Language Processing with many applications [1], such as sentiment analysis [2] [3], information search [4], ranking [5], and document classification [6]. The text classification model is generally divided into two categories: machine learning and deep learning.…”

Section: Introductionmentioning

confidence: 99%

Text Classification Using Long Short-Term Memory With GloVe Features

Sari

Rini

Malik

2020

Jurnal Ilmiah Teknik Elektro Komputer Dan Informatika

View full text Add to dashboard Cite

In the classification of traditional algorithms, problems of high features dimension and data sparseness often occur when classifying text. Classifying text with traditional machine learning algorithms has high efficiency and stability characteristics. However, it has certain limitations concerning largescale dataset training. In this case, a multi-label text classification technique is needed to be able to group four labels from the news article dataset. Deep Learning is a proposed method for solving problems in text classification techniques. This experiment was conducted using one of the methods of Deep Learning Recurrent Neural Network with the application of the architecture of Long Short-Term Memory (LSTM). In this study, the model is based on trial and error experiments using LSTM and 300-dimensional word embedding features with Global Vector (GloVe). By tuning the parameters and comparing the eight proposed LSTM models with a largescale dataset, to show that LSTM with features GloVe can achieve good performance in text classification. The results show that text classification using LSTM with GloVe obtain the highest accuracy is in the sixth model with 95.17, the average precision, recall, and F1-score are 95. Besides, LSTM with the GloVe feature gets graphic results that are close to good-fit on average.

show abstract

Sentiment Analysis Based on Weighted Word2vec and Att-LSTM

Cited by 11 publications

References 5 publications

Time-Weighted Cumulative LSTM Method Using Log Data for Predicting Credit Card Customer Turnover

Time-Weighted Cumulative LSTM Method Using Log Data for Predicting Credit Card Customer Turnover

Komparasi Ekstraksi Fitur dalam Klasifikasi Teks Multilabel Menggunakan Algoritma Machine Learning

Text Classification Using Long Short-Term Memory With GloVe Features

Contact Info

Product

Resources

About