| Summary: | 碩士 === 國立東華大學 === 資訊管理碩士學位學程 === 100 === In recent years, the online blogging community is growing bigger as a community network. Generally, we have used various blog search engines, such as Technorati, Blogpulse, and Google Blog Search, to find the blog post most appropriate for what we are seeking. However, the blogger often suffer an information overload problem because the blog posts are updated frequently from different blog search engines. We have encountered synonym (two terms are syntactically different but semantically interchangeable expressions) and polysemy (a term has different meanings) problems when we search from the blog search engine. In this paper, we use two semantic analysis models, Latent Semantic Analysis (LSA) and Probabilistic Latent Semantic Analysis (PLSA), to deal with these two problems. LSA uses a truncated Singular Value Decomposition (SVD) technique to capture the synonym relationships between terms. PLSA can deal with the problem of polysemy and can explicitly distinguish between different meanings and different types of term usage. According to the results of simulation analysis, we conclude that the semantic models can effectively be applied to the blog search engine.
|
|---|
