Indonesian Conjunction Rule Based Sentiment Analysis For Service Complaint Regional Water Utility Company Surabaya

Author(s):  
Auliya Anggraini ◽  
Entin Martiana Kusumaningtyas ◽  
Ali Ridho Barakbah ◽  
M Tafaquh Fiddin Al Islami
2005 ◽  
Vol 5 (2) ◽  
pp. 107-113
Author(s):  
F. Zuleta ◽  
A. Merlano ◽  
A. Alvarez ◽  
M. Montoya ◽  
E. Restrepo

A common characteristic of water utility and wastewater companies in developing countries is management problems and limited commercial vocation. In the biggest Latin American cities there is a level of infrastructure enough for providing a substantially better service than the one currently supplied to their badly served customers. For years decisions have moved between two extremes: public management – usually corrupted with playing politics and inefficiency problems, and privatization – sharply criticized by many, and which has shown tendencies to inequality that leave it far away from earning panacea status. This paper is intended to expose the advantages of a novel model in which a state-run company with commercial management problems, the EAAB, solves its limitations by keeping the ownership of its assets and successfully incorporating the participation of better practices from other specialized operators, one of which is a state-owned player, EEPPM. This scheme demonstrates how the service indicators of a system serving eight million inhabitants in the Colombian capital improved significantly with state-owned assets and private participation, without giving in to privatization pressures or stagnating in the usual inefficiency typical of public management in developing countries. This is proposed as a replicable experience that can be used in medium and large cities in other countries with similar management problems, with certain adjustments to fit the solution to the specific cases. This is also a practical case for conducting a comparison of competitiveness within a city, of interest for regulatory entities and investigators on the potential of comparative efficiency in a traditionally monopolistic industry.


Author(s):  
Isanka Rajapaksha ◽  
Chanika Ruchini Mudalige ◽  
Dilini Karunarathna ◽  
Nisansa de Silva ◽  
Gathika Rathnayaka ◽  
...  

2017 ◽  
Vol 52 (3) ◽  
pp. 2081-2097 ◽  
Author(s):  
Carlos Gómez-Rodríguez ◽  
Iago Alonso-Alonso ◽  
David Vilares

2022 ◽  
Vol 24 (3) ◽  
pp. 0-0

In this digital era, people are very keen to share their feedback about any product, services, or current issues on social networks and other platforms. A fine analysis of these feedbacks can give a clear picture of what people think about a particular topic. This work proposed an almost unsupervised Aspect Based Sentiment Analysis approach for textual reviews. Latent Dirichlet Allocation, along with linguistic rules, is used for aspect extraction. Aspects are ranked based on their probability distribution values and then clustered into predefined categories using frequent terms with domain knowledge. SentiWordNet lexicon uses for sentiment scoring and classification. The experiment with two popular datasets shows the superiority of our strategy as compared to existing methods. It shows the 85% average accuracy when tested on manually labeled data.


2019 ◽  
Vol 8 (4) ◽  
pp. 1809-1814

Sentiment analysis is a technique to analyze the people opinion, attitude, sentiment and emotion towards any particular object. Sentiment analysis has the following steps to predict the opinion of a review sentences. The steps are preprocessing, feature selection, classification and sentiment prediction. Preprocessing is the main important step and it consists of many techniques. They are Stop word Removal, punctuation removal, conversion of numbers to number names. Stemming is another important preprocessing technique which is used to transform the words in text into their grammatical root form and is mainly used to improve the retrieval of the information from the internet. It is applied mainly to get strengthen the retrieval of the information. Many morphological languages have immense amount of morphological deviation in the words. It triggered vast challenges. Many algorithms exist with different techniques and has several drawbacks. The aim of this paper is to propose a rule based stemmer that is a truncating stemmer. The new stemming mechanism in this paper has brought about many morphological changes. The new rule based morphological variation removable stemming algorithm is better than the existing other algorithms such as New Porter, Paice/Lovins and Lancaster stemming algorithm


Sign in / Sign up

Export Citation Format

Share Document