Effective Word Embedding for Twitter Data 


Vol. 43,  No. 11, pp. 1903-1910, Nov.  2018
10.7840/kics.2018.43.11.1903


PDF
  Abstract

In this paper, we provide guidelines for selections of learning model and learning parameter values for effective word embedding for Twitter data. The precedent studies on the model and parameters of the word embedding have been studied based on structured data such as news and Wikipedia, so it difficult to apply them to unstructured data such as Twitter. In this paper, we conducted experiment to analyze the performance change by selecting the learning model and adjusting the learning parameters using state-of-the-art word embedding technology, Word2Vec, for Twitter data and provide effective learning models and parameter values for good word embedding for twitter data.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

I. Kim and B. Jang, "Effective Word Embedding for Twitter Data," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 11, pp. 1903-1910, 2018. DOI: 10.7840/kics.2018.43.11.1903.

[ACM Style]

Inhwan Kim and Beakcheol Jang. 2018. Effective Word Embedding for Twitter Data. The Journal of Korean Institute of Communications and Information Sciences, 43, 11, (2018), 1903-1910. DOI: 10.7840/kics.2018.43.11.1903.

[KICS Style]

Inhwan Kim and Beakcheol Jang, "Effective Word Embedding for Twitter Data," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 11, pp. 1903-1910, 11. 2018. (https://doi.org/10.7840/kics.2018.43.11.1903)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880