SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHOD
With the advancement of social media and its growth, there is a lot of data that can be presented for research in social mining. Twitter is a microblogging that can be used. In this event, a lot of companies used the data on Twitter to analyze the satisfaction of their customer about product quality...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Mercu Buana
2020-04-01
|
| Series: | Jurnal Ilmiah SINERGI |
| Subjects: | |
| Online Access: | http://publikasi.mercubuana.ac.id/index.php/sinergi/article/view/5860 |
| _version_ | 1797710200355946496 |
|---|---|
| author | Mona Cindo Dian Palupi Rini Ermatita Ermatita |
| author_facet | Mona Cindo Dian Palupi Rini Ermatita Ermatita |
| author_sort | Mona Cindo |
| collection | DOAJ |
| description | With the advancement of social media and its growth, there is a lot of data that can be presented for research in social mining. Twitter is a microblogging that can be used. In this event, a lot of companies used the data on Twitter to analyze the satisfaction of their customer about product quality. On the other hand, a lot of users use social media to express their daily emotions. The case can be developed into a research study that can be used both to improve product quality, as well as to analyze the opinion on certain events. The research is often called sentiment analysis or opinion mining. While The previous research does a particularly useful feature for sentiment analysis, but it is still a lack of performance. Furthermore, they used Support Vector Machine as a classification method. On the other hand, most researchers found another classification method, which is considered more efficient such as Maximum Entropy. So, this research used two types of a dataset, the general opinion data, and the airline's opinion data. For feature extraction, we employ four feature extraction, such as pragmatic, lexical-grams, pos-grams, and sentiment lexical. For the classification, we use both of Support Vector Machine and Maximum Entropy to find the best result. In the end, the best result is performed by Maximum Entropy with 85,8% accuracy on general opinion data, and 92,6% accuracy on airlines opinion data. |
| first_indexed | 2024-03-12T06:48:44Z |
| format | Article |
| id | doaj.art-ec98c92064584a4794a318857c042535 |
| institution | Directory Open Access Journal |
| issn | 1410-2331 2460-1217 |
| language | English |
| last_indexed | 2024-03-12T06:48:44Z |
| publishDate | 2020-04-01 |
| publisher | Universitas Mercu Buana |
| record_format | Article |
| series | Jurnal Ilmiah SINERGI |
| spelling | doaj.art-ec98c92064584a4794a318857c0425352023-09-03T00:27:02ZengUniversitas Mercu BuanaJurnal Ilmiah SINERGI1410-23312460-12172020-04-01242879410.22441/sinergi.2020.2.0023366SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHODMona Cindo0Dian Palupi Rini1Ermatita Ermatita2Graduate Schoool of Computer Sciences, Universitas SriwijayaGraduate Schoool of Computer Sciences, Universitas SriwijayaGraduate Schoool of Computer Sciences, Universitas SriwijayaWith the advancement of social media and its growth, there is a lot of data that can be presented for research in social mining. Twitter is a microblogging that can be used. In this event, a lot of companies used the data on Twitter to analyze the satisfaction of their customer about product quality. On the other hand, a lot of users use social media to express their daily emotions. The case can be developed into a research study that can be used both to improve product quality, as well as to analyze the opinion on certain events. The research is often called sentiment analysis or opinion mining. While The previous research does a particularly useful feature for sentiment analysis, but it is still a lack of performance. Furthermore, they used Support Vector Machine as a classification method. On the other hand, most researchers found another classification method, which is considered more efficient such as Maximum Entropy. So, this research used two types of a dataset, the general opinion data, and the airline's opinion data. For feature extraction, we employ four feature extraction, such as pragmatic, lexical-grams, pos-grams, and sentiment lexical. For the classification, we use both of Support Vector Machine and Maximum Entropy to find the best result. In the end, the best result is performed by Maximum Entropy with 85,8% accuracy on general opinion data, and 92,6% accuracy on airlines opinion data.http://publikasi.mercubuana.ac.id/index.php/sinergi/article/view/5860microbloggingtwittersupport vector machinemaximum entropyfeature extraction |
| spellingShingle | Mona Cindo Dian Palupi Rini Ermatita Ermatita SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHOD Jurnal Ilmiah SINERGI microblogging support vector machine maximum entropy feature extraction |
| title | SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHOD |
| title_full | SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHOD |
| title_fullStr | SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHOD |
| title_full_unstemmed | SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHOD |
| title_short | SENTIMENT ANALYSIS ON TWITTER BY USING MAXIMUM ENTROPY AND SUPPORT VECTOR MACHINE METHOD |
| title_sort | sentiment analysis on twitter by using maximum entropy and support vector machine method |
| topic | microblogging support vector machine maximum entropy feature extraction |
| url | http://publikasi.mercubuana.ac.id/index.php/sinergi/article/view/5860 |
| work_keys_str_mv | AT monacindo sentimentanalysisontwitterbyusingmaximumentropyandsupportvectormachinemethod AT dianpalupirini sentimentanalysisontwitterbyusingmaximumentropyandsupportvectormachinemethod AT ermatitaermatita sentimentanalysisontwitterbyusingmaximumentropyandsupportvectormachinemethod |