In the digital and Internet era, companies are racing to profile their target users based on their online activities. One of the reliable sources is the news articles they read that can represent their interests. Howe...
详细信息
In the digital and Internet era, companies are racing to profile their target users based on their online activities. One of the reliable sources is the news articles they read that can represent their interests. However, extracting latent information from the news articles is not an easy task for a human. In this paper, we introduced a practical model to automatically extract latent information from news articles with pre-determined topics. Our proposed model used unsupervised learning, thus alleviating the need for humans to label news items manually. Doc2vec was used to generate word vectors for each article. Afterward, a spectral clustering algorithm was applied to group the data based on the similarity. A supervised Long Short Term Memory (LSTM) model was built to compare the clustering performance. The best 1, best 3, and best 5 scores were used to evaluate our model. The result showed that our model could not outperformed LSTM model for the best 1 score. However, the best 5 score result indicated that our model was sufficiently robust to cluster the articles based on topic similarity. Additionally, the proposed unsupervised model was implemented in both an on-premise server, and a cloud server. Surprisingly, our proposed method could run faster in the cloud server despite its less number of CPU cores.
Understanding how social structures with the use of a network have been an active field of study for academics in the past five years alone. The need to properly comprehends how Social Network Analysis (SNA) is being ...
详细信息
ISBN:
(纸本)9781665499705
Understanding how social structures with the use of a network have been an active field of study for academics in the past five years alone. The need to properly comprehends how Social Network Analysis (SNA) is being studied grows more and more in recent years. In this article, we propose a Systematic Literature Review (SLR) to the SNA to see how the algorithms, techniques, and methods are used also discuss their findings. We select thirty-one research studies on SNA. We found different algorithms and techniques that are being used. It is found that the selected research could be categorized into five different main topics which is academic, health, social media, communication, and technology. From all of the research paper discussed, it is also found that many algorithms and techniques are being used to enhanced the SNA, most of them are being machine learning algorithm such as Decision Tree, Random Forest, Support Vector Machine, Naïve Bayes, Logistic Regression, K Nearest Neighbor, and Whale Optimization Algorithm. While the common features of the datasets used in the research comes as different arrays of user information from social media platforms, Tweets and posts from multiple platforms, also a photographic input such as self-images, portraits, and context related pictures. This article will serve as a single reference for future researchers to the discovery of the latest SNA findings.
a furniture rental service multinational company has a mobile application that is used by the salesperson to make sales transactions. Currently the mobile application gets data from the ERP system by importing and exp...
详细信息
This paper purposes an improved algorithm of the butterfly lifecycle for calculating the performance of the company's growth. Three types of change for the better are regarding mathematical model, conception in ca...
详细信息
According to a survey from *** about in 2017, retail e-commerce sales worldwide amounted to 2.3 trillion US dollars and e-retail revenues are projected to grow to 4.88 trillion US dollars in 2021. Each year, e-commerc...
详细信息
Gotong royong (GORO) is an impressive cultural spirit of Indonesia. It means practically 'working together' without considering their dissimilarities and disparities to solve a problem. Specifically in public ...
详细信息
As e-commerce that covered all Indonesia, needs a fast reporting system to analyze the business to make the best decision. This paper provides methods to fasten the reporting process by making a data warehouse using K...
详细信息
Every enterprise stores and operates its transactions confidentially, therefore it has to encrypt the transaction to protect it from data intruders. Technically, most encryption processes are ranging from hundreds of ...
详细信息
Currently, digital online music increase significantly, both in terms of content and users. Increasing the number of digital music content every month conduce a lot of song catalog data and becoming unstructured and m...
详细信息
The problem of reporting service in *** is the complexity of the query to take the data from the table in oracle. There are many table to be processed for the data, because of that it's hard to show the report qui...
详细信息
暂无评论