scholarly journals Rule-based Sentiment Degree Measurement of Opinion Mining of Community Participatory in the Government of Surabaya

2018 ◽  
Vol 6 (2) ◽  
pp. 200-216 ◽  
Author(s):  
Berlian Juliartha Martin Putra ◽  
Afrida Helen ◽  
Ali Ridho Barakbah
Keyword(s):  
Data Collection ◽  
Sentiment Analysis ◽  
Opinion Mining ◽  
Task Complexity ◽  
Government Agency ◽  
Classification Algorithms ◽  
Bayes Classifier ◽  
Rule Based ◽  
The Government ◽  
New System

Diskominfo Surabaya, as a government agency, received much community participatory for improvement of governmental services, with increasing number of 698, 2717, 4176 and 4298 participatory data respectively in 2011, 2012, 2013 and 2014. It is challenging for Diskominfo Surabaya to set a target by giving the response back within 24 hours. Due to task complexity to address the degree of participatory and to categorize the group of participatory, they faced difficulty to fulfill the target. In this research, we present a new system for measuring the sentiment degree of community participatory. We provide 5 functions in our system, which are: (1) Data Collection, (2) Data Preprocessing, (3) Text Mining, (4) Sentiment Analysis and (5) Validation. We propose our rule-based technique for the sentiment analysis of opinion mining with detection of 8 important parts, which are (1) Verb, (2) Adjective, (3) Preposition, (4) Noun, (5) Adverb, (6) Symbol, (7) Phrase, and (8) Complimentary. For applicability of our proposed system, we made a series of experiment with 410 data of community participatory in Twitter for Diskominfo Surabaya and compared with other sentiment classification algorithms which are SVM and Naive Bayes Classifier. Our system performed 77.32% rate of accuracy and outperformed to other comparing algorithms.

scholarly journals Sentiment Analysis on Government Performance in Tourism During The COVID-19 Pandemic Period With Lexicon Based

CAUCHY ◽  
2021 ◽  
Vol 7 (1) ◽  
pp. 28-39
Author(s):  
Adri Priadana ◽  
Ahmad Ashril Rizal
Keyword(s):  
Sentiment Analysis ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Tourism Industry ◽  
Naive Bayes Classifier ◽  
Bayes Classifier ◽  
Naïve Bayes Classifier ◽  
Trending Topics ◽  
The Government ◽  
Negative Sentiment

The COVID-19 pandemic impact has affected all industries in Indonesia and even the world, including the tourism industry. Researchers have a role in researching to answer the needs of the tourism industry, especially in making tourism and business destination management programs and carrying out activities oriented to meet the needs of the tourism industry. Meanwhile, the government has a role in making policies, especially in the roadmap, for developing the tourism industry. This study aims to track trending topics in social media Instagram since COVID-19 hit. The results of trending topics will be classified by sentiment analysis using a Lexicon-based and Naive Bayes Classifier. Based on Instagram data taken since January 2020, it shows the five highest topics in the tourism sector, namely health protocols, hotels, homes, streets, and beaches. Of the five topics, sentiment analysis was carried out with the Lexicon-based and Naive Bayes classifier, showing that beaches get an incredibly positive sentiment, namely 80.87%, and hotels provide the highest negative sentiment 57.89%. The accuracy of the Confusion matrix's sentiment results shows that the accuracy, precision, and recall are 82.53%, 86.99%, and 83.43%, respectively.

scholarly journals Analisis Sentimen Sistem E-Tilang Menggunakan Algoritma Naive Bayes Dengan Optimalisasi Information Gain

2020 ◽  
Vol 1 (1) ◽  
pp. 19-26
Author(s):  
Rakhmi Khalida ◽  
Siti Setiawati
Keyword(s):  
Sentiment Analysis ◽  
Opinion Mining ◽  
Naive Bayes ◽  
Information Gain ◽  
Naïve Bayes ◽  
Traffic Violations ◽  
The Government ◽  
Bayes Algorithm ◽  
User Friendly

Abstract   The Government of Indonesia took steps to change the system to improve public services in traffic violations by implementing the e-ticketing system. This system is a solution for disciplining motorized motorists from committing traffic violations. The existence of e-ticketing is also a solution to prevent the delinquency of law enforcers from illegal levies, peace terms in place, to accountability of fines. In this study, sentiment analysis of the e-ticketing system or opinion mining to classify the variety of public comments that give a positive, negative or neutral impression. Twitter social media is one of the objects to express opinions because it is user friendly, updated topics, and openly accesses tweets. Opinions on Twitter are collected, then the preprocessing stage is performed, then the selection of information gain features helps reduce noise caused by irrelevant labels, the next step is the classification of sentiments with the Naïve Bayes algorithm and finally polarity sentiments. This research resulted in an accuracy of 41.82%, a precision of 50.51% and a recall of 45.45%.   Keywords: Sentiment analysis, E-ticketing, Information Gain, Naive Bayes   Abstrak   Pemerintah Indonesia melakukan langkah perubahan untuk memperbaiki sistem pelayanan publik dalam pelanggaran berlalu-lintas yaitu dengan menerapkan sistem e-Tilang. Sistem ini menjadi solusi mendisiplinkan para pengendara kendaraan bermotor dari banyaknya melakukan pelanggaran berlalu-lintas. Keberadaan e-Tilang juga menjadi solusi mencegah kenakalan penegak hukum dari pungutan liar, istilah damai ditempat, hingga akuntabilitas uang denda. Dalam penelitian ini melakukan analisis sentimen tentang sistem e-Tilang atau opinion mining untuk mengelompokan ragam komentar masyarakat yang memberikan kesan positif, negatif atau netral. Media sosial Twitter menjadi salah satu objek untuk menyampaikan opini karena user friendly, topik ter-update, dan terbuka mengakses tweet. Opini pada twitter dikumpulkan, lalu dilakukan tahapan preprocessing, selanjutnya dengan seleksi fitur information gain membantu mengurangi noise yang disebabkan oleh label-label yang tidak relevan, tahap selanjutnya adalah klasifikasi sentimen dengan algoritma Naïve Bayes dan terakhir sentimen polarity. Penelitian ini menghasilkan accuracy 41,82%, presisi 50,51% dan recall 45,45%.   Kata kunci: Analisis sentimen, E-Tilang, Information Gain, Naive Bayes

scholarly journals Product Recommendation System based on User Trustworthiness & Sentiment Analysis

2020 ◽  
Vol 32 ◽  
pp. 03030
Author(s):  
Gunjeet Kaur Soor ◽  
Amey Morje ◽  
Rohit Dalal ◽  
Deepali Vora
Keyword(s):  
Sentiment Analysis ◽  
Recommendation System ◽  
Opinion Mining ◽  
Product Recommendation ◽  
Fake Reviews ◽  
New System

The current online product recommendation system based on reviews has many limitations due to randomness in the review patterns. The data which is used are the reviews and ratings from the e-commerce websites. This data might contain fake reviews that make the data uncertain. Due to this, the currently existing systems produce ambiguous results on this present data. Instead of this, the new system uses only genuine reviews, considering the trustworthiness of the user and generates the results in a more significant manner. The proposed system scrapes reviews from different online websites and performs opinion mining and sentiment analysis on it. Other factors like star ratings, the buyer’s profile and previous purchases and whether the review has been given after purchasing or not are included. Based on these factors & user trustworthiness, the website from which the user should buy the product will be recommended.

scholarly journals ANALISIS IMPLEMENTASI LAPORAN AKUNTABILITAS KINERJA INSTANSI PEMERINTAH PADA DINAS LINGKUNGAN HIDUP DAN KEBERSIHAN KOTA KUPANG

2019 ◽  
Vol 7 (1) ◽  
pp. 21-33
Author(s):  
Ernel Gustino Susang ◽  
Sarinah Joyce Margaret Rafael
Keyword(s):  
Data Analysis ◽  
Data Collection ◽  
Qualitative Study ◽  
Comparative Method ◽  
Government Agency ◽  
Study Data ◽  
Analysis Technique ◽  
Performance Accountability ◽  
Interview Methods ◽  
The Government

Penelitian ini bertujuan untuk mengetahui kesesuaian antara kinerja Laporan Akuntabilitas Kinerja Instansi Pemerintah (LAKIP) Dinas Lingkungan Hidup dan Kebersihan Kota Kupang terhadap kinerja di lapangan. Penelitian ini merupakan penelitian kualitatif deskriptif. Pengumpulan data menggunakan metode wawancara, dokumentasi, dan kuesioner. Teknik analisis data yang digunakan adalah analisis dengan metode komparatif. Hasil penelitian menunjukkan bahwa Kinerja OPD di lapangan belum sesuai dengan kinerja dalam LAKIP 2017. Kata kunci : LAKIP, OPD, Dinas Lingkungan Hidup dan Kebersihan   This research aims to find out the suitability between the performance of the Government Agency Performance Accountability Report (LAKIP) of the Environment and Clean Departement of the Kupang City in the field. This research is a descriptive qualitative study. Data collection uses interview methods, documentation, and questionnaires. The data analysis technique used is analysis with a comparative method. The results showed that the performance of OPD in the field was not in line with the performance in LAKIP 2017. Keywords: LAKIP, OPD, Environmental and Clean Departement

scholarly journals Sentiment Analysis and Opinion Summarization of Product Feedback

2019 ◽  
Vol 8 (2S4) ◽  
pp. 59-64
Keyword(s):  
Artificial Intelligence ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Opinion Mining ◽  
Online Shopping ◽  
User Interaction ◽  
Decision Making Process ◽  
Rule Based ◽  
Opinion Summarization ◽  
Rule Based Approach

With the exponential growth of online shopping platforms, user interaction is made direct through their reviews and ratings. User’s opinions and experiences are a significant source of valuable information in decision making process. In recent days, almost every website encourages users to express and exchange their views, suggestions and opinions related to product, services, policies, etc. publicly. Opinion mining is an extensive branch of Artificial Intelligence and a form of Natural Language Processing which illustrates the attitude of the customers, in specific services or products. Also known as Sentiment Analysis, it aims at determining the response and mood or attitude of the speaker or the overall contextual and emotional polarity or reaction. Existing algorithms determine sentiment by training on datasets, lexicon-based approach by calculating polarity and rule-based approach for classification. Opinion Summarization is the process of consolidating a large amount of sentiments and opinions into a clear and brief statement for an easier grasp on the underlying context. Major summarization methods include, Extractive method, Sentence Ranking, Abstractive method and Clustering of Textual Segments. Hence it is important to judge and classify these reviews and present a laconic opinion so it would be easier for users to obtain a gist and overall polarity on the various reviews instead of going through all of them

scholarly journals Impact of Demonetization in India using Opinion Mining over Twitter Data

2020 ◽  
pp. 562-568
Author(s):  
Mrugendrasinh Rahevar ◽  
Martin Parmar ◽  
Rekha Karangiya
Keyword(s):  
Social Networks ◽  
Sentiment Analysis ◽  
Opinion Mining ◽  
Daily Basis ◽  
The Public ◽  
Everyday Activities ◽  
Large Numbers ◽  
The Everyday ◽  
The Government ◽  
Media Forum

In recent years, the utilization of Internet has turned out to be one of the everyday activities in our life. Social networks constitute a noteworthy segment of the Web and made an upheaval. It incorporates social media, forum conversations, blogs and micro-blogs like twitter. Due to this, large numbers of comments are produced on daily basis. So, nowadays most of the researchers or analyzers are concentrating on extracting significant data from social networks in order to understand the public viewpoint. This research has been reached out outside the computer science to cover other areas like business, political and social science. Hence, Sentiment analysis and Opinion mining are popular field of research in Data mining. This paper delineates various aspects of sentiment analysis in detail inclusive of important concepts, classification, process, importance, challenges and applications. The following paper presents experiment on sentiment analysis of public opinion on demonetization in India. Sentiment analysis is performed on tweets related to demonetization in India extracted from twitter. Polarity of the opinion is observed through the experimental analysis. Through the outcome of this analysis, the sentiments of the citizens that are determined help the government in improving their decisions and work for the welfare of the citizens.

scholarly journals Data Analysis and Sentiment Analysis on Amazon Reviews

2021 ◽  
Vol 9 (12) ◽  
pp. 2200-2206
Author(s):  
Raj Sinha
Keyword(s):  
Data Analysis ◽  
Sentiment Analysis ◽  
Opinion Mining ◽  
Research Field ◽  
Classification Algorithms ◽  
Product Reviews ◽  
Human Language ◽  
Using Data ◽  
The Given ◽  
Automatic Systems

Abstract: In the present scenario, a person wants ease in their lives, so E-commerce has become a great and admirable involvement in providing the availability of any product at the doorsteps. But how a person can know the efficiency and originality of the product just by looking at the pictures and the details of the product on the websites. To overcome these issues the E-commerce websites have introduced the concept of the Reviews. Reviews are written by the customers who have already purchased it. Studies show that Product reviews are one of the most important points one considers during the purchasing from E-commerce websites like Flipkart, Snapdeal, Amazon and so on. This paper proposes a model that detects whether the given review is positive, negative, or neutral using the method of sentiment analysis. And using Data Analysis we can find the extension of this paper, we are planning to use a type of sentiment analysis, Opinion Mining which is the research field that predominantly makes automatic systems that will find opinion from the text written in human language. Using opinion mining, we can find whether the given reviews are fake or not. In this paper we have used Amazon food reviews data and based on the rating given by the user we are classifying reviews as positive, negative, or neutral. For positive review ratings given were 4 and 5. For negative review ratings given were 1 and 2. For neutral, rating given was 3. Based on these ratings, we are performing sentiment analysis using Scikit Learn and finding the accuracies of various classification algorithms. We are using Jupyter Notebook for visualization of documents and live coding. Keywords: Data analysis, classification algorithms, data visualization, machine learning

Sign in / Sign up

Export Citation Format

Share Document