Efficient Algorithms for Preprocessing and Stemming of Tweets in a Sentiment Analysis System

Khafaji, Hussein K.; Habeeb, Areej Tarief

doi:10.9790/0661-1903024450

Cited by 15 publications

(11 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Penggunaan jejaring sosial atau media sosial semakin bertambah, ini sebagai bukti dari perkembangan internet yang mempengaruhi media komunikasi [1]. Media sosial sudah menjadi bagian terpenting untuk percakapan di seluruh dunia, karena orang-orang dapat dengan bebas mengekspresikan sebuah pendapat tentang suatu objek yang ada [2].…”

Section: Pendahuluanunclassified

“…[4] Penggunaan jejaring sosial atau media sosial semakin bertambah, ini sebagai bukti dari perkembangan internet yang mempengaruhi media komunikasi. Media sosial sudah menjadi bagian terpenting untuk percakapan di seluruh dunia, karena orang-orang dapat dengan bebas mengekspresikan sebuah pendapat tentang suatu objek yang ada [14] Pada tahun 2018, Fanisa, S., dkk dengan menggunakan metode Naïve Bayes dan seleksi fitur Query Expansion Rangking melakukan penelitian untuk sentiment analysis terhadap pariwisata di Kota Malang. Dari hasil pengujian penelitian ini uji akurasi dengan menggunakan variasi rasio seleksi fitur menghasilkan akurasi terbaik 86,6% [5].…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Penerapan Algoritma Sentimen Analysis dan Naïve Bayes terhadap opini pengunjung di tempat wisata pantai Pintu Kota, Kota Ambon

Aponno¹

2022

JATISI

View full text Add to dashboard Cite

In the current development of information technology, sentiment analysis is often used as a tool to seek public opinion about something. Naive Bayes analysis is a method of classifying data based on simple probabilities and is designed to be used with the assumption that there is no interdependence between one class and another. The purpose of this study was to determine public opinion about visitor satisfaction at Pintu Kota Ambon by testing positive and negative recall values, as well as positive and negative precision values and accuracy values using sentiment analysis and naive Bayes analysis. All data are processed using RapidMiner tools. In this survey, we obtained data from the results of the search for comments from visitors to the Pintu Kota Ambon attraction on the Google Maps website. The results obtained from this study indicate that the tracking of sentiment analysis and Naive Bayes analysis of the opinions of 113 visitors showed a negative recall value of 97.62% and a negative recall value of 83.33%.The negative accuracy value is 85.42%, while the positive accuracy value is 97.22% From these results obtained an accuracy value of 90.65%.From the results of the analysis, tourist destinations at Ambon City Gate are considered good because they get a high accurate value of 90.65%. From this research, it can be concluded that it is necessary to develop an information system to track visitor satisfaction in other tourist destinations.

show abstract

Section: Pendahuluanunclassified

Penerapan Algoritma Sentimen Analysis dan Naïve Bayes terhadap opini pengunjung di tempat wisata pantai Pintu Kota, Kota Ambon

Aponno¹

2022

JATISI

View full text Add to dashboard Cite

show abstract

“…(3) Convert slang words (Normalization) are used to convert slang words into standard words [13], such as the word "tdk" to "tidak". (4) Tokenization is a technique to change the text in a document in the form of tokens or words [14]. (5) Cleaning the text of words that are considered unimportant such as "dan", "di", "itu", etc.…”

Section: Preprocessing Datamentioning

confidence: 99%

Sentiment Analysis Based on Aspects Using FastText Feature Expansion and NBSVM Classification Method

Lestari

Setiawan

2022

JoSYC

View full text Add to dashboard Cite

Telkomsel is a service that the people of Indonesia widely use. Complaints from users referring to Telkomsel's service and signal aspects are often made in Twitter tweets with harsh or good language. This is done because users continue to demand to get better service. Therefore, an aspect-based sentiment analysis technique is needed to determine a person's view of each aspect, such as Telkomsel's service and signal aspects. Aspect-based sentiment analysis is a solution to find out the opinions of Telkomsel users based on their aspects. In its implementation, the NBSVM method is used as a classification model that is proven to work well compared to other methods, namely MNB and SVM. The implementation of the expansion of the FastText feature can affect the level of performance model, and the best results are obtained in the Top 1 feature on the signal aspect and Top 5 on the service aspect with a combination of Twitter corpus and news. In this study, the data used is unbalanced and has been handled by applying SMOTE and AdaBoost techniques to the FastText feature expansion model. Based on the results of the tests that have been carried out, SMOTE can handle data imbalances compared to AdaBoost. The performance results of the FastText feature expansion model after SMOTE are applied to get F1-Score 91.24% in the signal aspect and F1-Score 88.75% in the service aspect.

show abstract

“…Preprocessing: Preprocessing methods include filtering the data communicated from the fog layer; this step consumes roughly 85% of knowledge discovery time [ 33 ] to filter the data. We followed several steps as follows: Keywords extraction : Since the platform we were working on is Twitter, we selected a set of the most used hashtags and collected our tweets based on it.…”

Section: Proposed Sns Big Data Analysis Frameworkmentioning

confidence: 99%

SNS Big Data Analysis Framework for COVID-19 Outbreak Prediction in Smart Healthy City

Azzaoui

Singh

Park

2021

Sustainable Cities and Society

View full text Add to dashboard Cite

Nowadays, the world is experiencing a pandemic crisis due to the spread of COVID-19, a novel coronavirus disease. The contamination rate and death cases are expeditiously increasing. Simultaneously, people are no longer relying on traditional news channels to enlighten themselves about the epidemic situation. Alternately, smart cities citizens are relying more on Social Network Service (SNS) to follow the latest news and information regarding the outbreak, share their opinions, and express their feelings and symptoms. In this paper, we propose an SNS Big Data Analysis Framework for COVID-19 Outbreak Prediction in Smart Sustainable Healthy City, where Twitter platform is adopted. Over 1000 Tweets were collected during two months, 38% of users aged between 18 and 29, while 26% are between 30 and 49 years old. 56% of them are males and 44% are females. The geospatial location is USA, and the used language is English. Natural Language Processing (NLP) is deployed to filter the tweets. Results demonstrated an outbreak cluster predicted seven days earlier than the confirmed cases with an indicator of 0.989. Analyzing data from SNS platforms enabled predicting future outbreaks several days earlier, and scientifically reduce the infection rate in a smart sustainable healthy city environment.

show abstract

Efficient Algorithms for Preprocessing and Stemming of Tweets in a Sentiment Analysis System

Cited by 15 publications

References 4 publications

Penerapan Algoritma Sentimen Analysis dan Naïve Bayes terhadap opini pengunjung di tempat wisata pantai Pintu Kota, Kota Ambon

Penerapan Algoritma Sentimen Analysis dan Naïve Bayes terhadap opini pengunjung di tempat wisata pantai Pintu Kota, Kota Ambon

Sentiment Analysis Based on Aspects Using FastText Feature Expansion and NBSVM Classification Method

SNS Big Data Analysis Framework for COVID-19 Outbreak Prediction in Smart Healthy City

Contact Info

Product

Resources

About