Prediction of Company's Trend based on Publication Statistics and Sentiment Analysis
Prediction of Company's Trend based on Publication Statistics and Sentiment Analysis
复制标题
DOI：
10.5220/0006048602830290
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Fumiyo Fukumoto;Yoshimi Suzuki;Akihiro Nonaka;Karman Chan
中科院分区：
文献类型：
--
作者：
Fumiyo Fukumoto;Yoshimi Suzuki;Akihiro Nonaka;Karman Chan
本文提出了一种预测公司在商业领域研发（R&D）趋势的方法。我们使用了三类数据集合，即科学论文、公开专利和报纸文章，来评估公司商业领域趋势的时间变化。我们对按时间序列发表的科学论文和公开专利进行频次统计。对于新闻文章，我们运用情感分析来提取与公司商业领域相关的正面新闻报道，并统计其出现频次。然后，针对每家公司，我们基于这些频次统计数据生成时间变化情况。对于每个商业领域，我们对这些时间变化进行聚类。最后，我们为每个聚类估计预测模型。结果表明，结合三类数据所得到的模型能有效地预测公司未来趋势，特别是结果显示，SP聚类对整体性能有贡献。
This paper presents a method for predicting companyâs trend on research and development(R&D) in business area. We used three types of data collections, i.e, scientific papers, open patents, and newspaper articles to estimate temporal changes of trends on companyâs business area. We used frequency counts on scientific papers and open patents to be published in time series. For news articles, we applied sentiment analysis to extract positive news reports related to the companyâs business areas, and count their frequencies. For each company, we then created temporal changes based on these frequency statistics. For each business area, we clustered these temporal changes. Finally, we estimated prediction models for each cluster. The results show that the the model obtained by combining three data is effective to predict companyâs future trends, especially the results show that SP clustering contributes overall performance.