Description

Exploring potentially useful information from huge amount of textual data produced by micro blogging services has attracted much attention in recent years. An important preprocessing step of micro blog text mining is to convert natural language texts into proper numerical representations. Due to the short-length characteristics of micro blog texts, using term frequency vectors to represent micro blog texts will cause “sparse data” problem. Finding proper representations of micro blog texts is a challenging issue. In this paper, we apply deep networks to map the high-dimensional representations of micro blog texts to low-dimensional representations. To improve the result of dimensionality reduction, we take advantage of the semantic similarity derived from two types of micro blog-specific information, namely the retweet relationship and hash tags. Two types of approaches, including modifying training data and modifying the training objective of deep networks, are proposed to make use of microblog-specific infor mation. Experiment results show that the deep models perfor m better than traditional dimensionality reduction methods such as latent semantic analysis and latent Dirichlet allocation topic model, and the use of microblog-specific infor ma tion can help to learn better representations.