دانلود رایگان مقاله بررسی های آنلاین در زمینه نظارت بر ایمنی اسباب بازی ها

Abstract

Toy-related injuries account for a significant number of childhood injuries and the prevention of these injuries remains a goal for regulatory agencies and manufacturers. Text-mining is an increasingly prevalent method for uncovering the significance of words using big data. This research sets out to determine the effectiveness of text-mining in uncovering potentially dangerous children's toys. We develop a danger word list, also known as a “smoke word” list, from injury and recall text narratives. We then use the smoke word lists to score over one million Amazon reviews, with the top scores denoting potential safety concerns. We compare the smoke word list to conventional sentiment analysis techniques, in terms of both word overlap and effectiveness. We find that smoke word lists are highly distinct from conventional sentiment dictionaries and provide a statistically significant method for identifying safety concerns in children's toy reviews. Our findings indicate that text-mining is, in fact, an effective method for the surveillance of safety concerns in children's toys and could be a gateway to effective prevention of toy product-related injuries.

8. Summary and conclusions

In this paper we evaluated a text mining approach for discovering safety concerns mentioned in children's toy reviews. We adapted prior defect discovery systems [3–5] to the children's toy industry. We used public U.S. CPSC records to develop two different “smoke lists”: one from CPSC National Electronic Injury Surveillance System (NEISS) narratives and the other from CPSC Recall reports. We used these smoke lists to score over one million Amazon reviews under the category “Toys and Games”. We conducted three experiments to determine the effectiveness of the smoke list approaches, and contrast to sentiment approaches. We determined that this customized approach was indeed effective, using both chi-squared and t-tests of statistical significance.