Name
Abstract | ||
|---|---|---|
Evaluating the performance of meteorological service not only relies on physical measurements but also requires public feedback. As a significant part of the evaluation, assessing the sentiment of these feedbacks gives an insightful view which can help to establish reliable decision support in policy making and emergency responding. However, climate and weather are always accompanying phenomena in the evolutionary process of human beings, making the climate and weather-related words themselves contain a large number of extend meanings in peopleu0027s daily expression. These polysemy phenomena have led to a decline in the performance of traditional general sentiment calculations in the vertical field of meteorology. As far as we know, there is no Chinese sentiment calculation tool in the meteorological field, due to the different expressions between different languages. Facing with the above problems and issues, this paper proposes and establishes a sentiment analysis based on lexicon-based framework of Chinese text in the meteorological field. The framework fuses two major sentiment assessment method consists of two approaches, namely machine learning-based and knowledge based one. First, word embedding similarity and word co-occurrence methods are utilized to construct the domain sentiment dictionary which includes 8,796 negative words and 4,751 positive words. Then, by using the extend sentiment dictionary to select theme words from original text as feature, machine learning models are introduced to assess the sentiment tendency. Experiment showed that the performance of the proposed framework was improved up to 85.79% in terms of overall accuracy compared with traditional methods. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00244 | ISPA/BDCloud/SocialCom/SustainCom |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
15 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yinan Li | 1 | 74 | 12.35 |
| Fuquan Zhang | 2 | 4 | 3.11 |
| Yifan Zhu | 3 | 30 | 7.34 |
| Sifan Zhang | 4 | 7 | 1.42 |
| Yu Mao | 5 | 0 | 0.68 |
| Zhendong Niu | 6 | 548 | 67.31 |