HCI in Business, Government, and Organizations: 5th International Conference, HCIBGO 2018, Las Vegas, NV, July 15-20: Proceedings
It is a widely accepted truth there are great values embedded in the opinion and sentiment expressed by users on social media platforms. Nowadays, it is quite common for researchers or engineers to adopt opinion mining and sentiment analysis techniques to extract enriched emotional information from...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Institutional Knowledge at Singapore Management University
2018
|
| Subjects: | |
| Online Access: | https://ink.library.smu.edu.sg/sis_research/10029 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Singapore Management University |
| Language: | English |
| Summary: | It is a widely accepted truth there are great values embedded in the opinion and sentiment expressed by users on social media platforms. Nowadays, it is quite common for researchers or engineers to adopt opinion mining and sentiment analysis techniques to extract enriched emotional information from online text content. However, given the characteristics of social media, such as dynamic, short, informal and context dependent, applying general opinion mining and sentiment analysis techniques originally designed for static long text corpora would lead to serious bias. In many applications, even research that not specialized in opinion mining and sentiment analysis, this problem is ignored unintentionally or unintentionally. Such ignorance may contribute the failure of some designs or unexplainable results. In this paper, we summarized these challenges in social media sentiment analysis. Some potential solutions for these challenges are also discussed. Finally, we also introduced several state-of-the-art techniques in social media sentiment analysis. |
|---|