Search results

This research addresses the challenge of polysemous words in word embedding techniques, which are commonly used in text mining. It aims to resolve word sense ambiguity by introducing a social network sense disambiguation (SNSD) model based on social network analysis (SNA).

The SNSD model treats words as members of a social network and their co-occurrence relationships as interactions. By analyzing these interactions, the model identifies words with high betweenness centrality, which may act as bridges between different word sense communities, indicating polysemy. This unsupervised method does not rely on pre-tagged resources and is validated using the IMDb dataset.

The SNSD model effectively resolves word sense ambiguity in word embeddings, proving to be a cost-effective and adaptable solution to this issue. The experimental results demonstrate that the model enhances the accuracy of word embeddings by accurately identifying the correct meanings of polysemous words.

This study is the first to apply SNA to word sense disambiguation (WSD). The SNSD model offers a novel, unsupervised approach that overcomes the limitations of traditional supervised or knowledge-based methods, providing a valuable contribution to the field of text mining.

Purpose – This chapter examines how drug prescribing behavior in Taiwanese hospitals changed after the government changed reimbursement systems. In 2002, Taiwan instituted a system in which hospitals are reimbursed for drug expenditures at full price from a fixed global budget before the remaining budget is allocated to reimburse all other expenditures, often at discounted prices. Providers are thus given a financial incentive to increase prescriptions.

Methodology – We isolate the effect of this system from that of other confounding factors by estimating a difference-in-difference model to analyze monthly drug expenditures of hospital departments for outpatients during the years 1999–2006.

Findings – Our results suggest that hospital departments which use drugs more heavily as part of their regular medical care increased their drug prescription expenditures after the implementation of the global budget system. In addition, we find that the response was stronger among for-profit than not-for-profit and public hospitals.

Implications – Hospital doctors responded to the financial incentive created by the particular global budgeting system adopted in Taiwan by increasing expenditures on drug treatments for outpatients.