Multi-domain active learning for text classification

Li, Lianghao; Jin, Xiaoming; Pan, Sinno Jialin; Sun, Ju

doi:10.1145/2339530.2339701

Cited by 60 publications

(33 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Penggunaan dataset lintas domain, biasanya dipakai untuk mengatasi kurangnya data berlabel yang digunakan dalam proses klasifikasi [13] [14]. Dataset diambil dari domain lain yang telah memiliki label, dan memiliki data dalam jumlah besar.…”

Section: Klasifikasi Lintas Domainunclassified

Klasifikasi Ulasan Aplikasi Pada Toko Aplikasi Bergerak Dengan Memanfaatkan Issue Tracker Github

Prasetyo¹,

Siahaan²

2017

JUTI

View full text Add to dashboard Cite

show abstract

Section: Klasifikasi Lintas Domainunclassified

Klasifikasi Ulasan Aplikasi Pada Toko Aplikasi Bergerak Dengan Memanfaatkan Issue Tracker Github

Prasetyo¹,

Siahaan²

2017

JUTI

View full text Add to dashboard Cite

show abstract

“…Lianghaoet al 2 proposed a novel multi-domain active learning framework. This framework jointly selects text data from all domains such as BOOKS, DVD, Electronics and Kitchen from Amazon.com.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of Features on Sentimental Analysis

Shahana¹,

Omman²

2015

Procedia Computer Science

View full text Add to dashboard Cite

Sentimental analysis is the method of finding sentiment such as positive or negative from a text data. In this paper we are using some feature selection techniques such as Mutual information, Chi-Square, Information gain and TF-idf to select features from high dimensionality of feature set. These methods are evaluated over the dataset which contains 2000 review data about MOVIES. The classification is performed using support vector machine provided by weka 9 tool. We also investigate that which is best feature to extract sentiments from the reviews. We are considering unigram, bigram,POS tags of words and function words as our feature set.

show abstract

“…Telemonitoring has provided an efficient and effective solution to problems faced in the healthcare field, such as crowded hospitals or clinics in developing countries. Telemedicine can include smart-home monitoring whereby special homes have sensor devices installed on the walls and in particular areas of the patient's living environment [17]. These sensors could attached to the floor to measure the motion and speed made by the aged patient and help prevent her/him from falling.…”

Section: Telemedicine In Healthcarementioning

confidence: 99%

“…Another type of sensor is a radio-frequency identification (RFID) that helps people in alzheimer or dementia. With special applications, smart phones can also be used to assist in capturing unusual sounds, for example, crying for help [17], or the users' movement from one place to another to detect wandering of aged people at early stage [7,24]. Li et al [17] have pointed out important role played by telemedicine in healthcare industry:…”

Section: Telemedicine In Healthcarementioning

confidence: 99%

Telemedicine and Telemonitoring in Healthcare

Alsgaer

Tao

Zhang

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Over the last decade, there has been an increasing demand of information technology, specifically, telemedicine and telemonitoring in healthcare. Many elderly and disabled people are unable to look after themselves. They also desire quality healthcare. If the healthcare can be provided at home instead of only hospitals, the service could be more affordable, and people would feel more comfortable. Aiming to help elderly and disabled people, technology has been developed to provide assistance in various ways. Consequently, telemedicine and telemonitoring have been deeply embedded in healthcare industry and made significant impact. This report has provided a comprehensive review covering current progress of research in telemedicine and telemonitoring and their applications to healthcare services.

show abstract

Multi-domain active learning for text classification

Cited by 60 publications

References 18 publications

Klasifikasi Ulasan Aplikasi Pada Toko Aplikasi Bergerak Dengan Memanfaatkan Issue Tracker Github

Klasifikasi Ulasan Aplikasi Pada Toko Aplikasi Bergerak Dengan Memanfaatkan Issue Tracker Github

Evaluation of Features on Sentimental Analysis

Telemedicine and Telemonitoring in Healthcare

Contact Info

Product

Resources

About