Extraction and Visualization of Trend Information from Newspaper Articles and Blogs

Trend information is a summarization of temporal statistical data, such as changes in product prices and sales. We propose a method for extracting trend in-formation from multiple newspaper articles and blogs, and visualizing the information as graphs. As target texts for extraction of trend information, the MuST (Multimodal Summarization for Trend Information) workshop focuses on newspaper articles. In addition to newspapers, we focus on blogs, because useful in-formation for analysing trend information is often written in blogs, such as the reasons for in-creases/decreases of statistics and the impact of in-creases/decreases of statistics on society. To extract trend information, we extract temporal expressions and statistical values, and we devised methods for both operations. To investigate the effectiveness of our methods, we conducted some experiments. We obtained a recall of 6.3 % and precision of 31.3 % for newspaper articles, and a recall of 44.8 % and preci-sion of 60.3 % for blogs. From the error analysis, we found that most errors in newspaper articles were caused by misconversion of temporal expressions such as “同年 ” (the same year) or “前月 ” (the pre-vious month), into “YYYY-MM-DD ” form, although temporal expressions were detected correctly. In con-trast to newspaper articles, there are few temporal expressions in blogs for which resolution is required, such as “同日 ” (the same day) or “前月 ” (the previ-ous month). As a result, recall and precision for blogs are higher than those for newspaper articles