A sentiment analysis framework in implicit opinions for Thai language

Masdisornchote, Masawee

doi:10.1109/iecon.2015.7392125

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also includes characters that do not exist on the keyboard, such as "α," "β," and "π." Research on special symbols includes Tapang (2016), Masdisornchote (2016), Charoensuk and Sornil (2018), and Sirihattasak (2019). 2.…”

Section: Stopword Removalmentioning

confidence: 99%

“…However, the use of word attribute does not consider word placement, word efficiency, or quality in constructing a discriminant model. The verbal feature has also been used in research samples (Chumwatana, 2015;Masdisornchote, 2016;Laosungsuk et al, 2017;Saensuk et al, 2019).…”

Section: Wordmentioning

confidence: 99%

“…It will be classified as positive if the message contains the words "delicious" or "good." The lexical classification method is used on research that categorizes text by topic, emotion, or feeling (Pugsee & Niyomvanich, 2015;Wansopha et al, 2015;Songram, 2016;Tapang, 2016;Masdisornchote, 2016). The machine learning (ML) approach uses model development from the sample dataset where the answer is assigned.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Automatic Text Classification Based on Thai Social Media Data

Tanantong

Parnkow

2022

International Journal of Knowledge and Systems Science

View full text Add to dashboard Cite

In the digital age, the information on social media, such as Facebook, Twitter, and Instagram, is increasing rapidly. Therefore, it has led to studies and researches on social media analytics to extract useful models or knowledge from the data. One of the most interesting topics in social media analytics is text classification on social media data. However, since social media data has a diverse and complex data structure, text analysis and classification are considered a challenging issue that requires a specific technique to implement. The objective of this review paper is to collect and review research related to the automatic classification of Thai text on social media by presenting and explaining the process of text classification on various issues. These include data collection and data sources, amount of data and data preparation for research, feature extraction methods, text classification automated modeling methods, efficacy evaluation and measurement methods, the results of text classification, and summary of the overall trend of research on the topic.

show abstract

Section: Stopword Removalmentioning

confidence: 99%