Icon

JKISeasor2-20_​tomljh_​ver1

There has been no title set for this workflow's metadata.

Challenge 20: Topics in Hotel Reviews
Level: Hard

Description: You work for a travel agency and want to better understand how hotels are reviewed online. What topics are common in the reviews as a whole, and what terms are most relevant in each topic? How about when you separate the reviews per rating? A colleague has already crawled and preprocessed the reviews for you, so your job now is to identify relevant topics in the reviews, and explore their key terms. What do the reviews uncover? Hint: Topic Extraction can be very helpful in tackling this challenge. Hint 2: Coherence and perplexity are metrics that can help you pick a meaningful number of topics.

挑战20:酒店点评主题水平: 硬描述:您在一家旅行社工作,想更好地了解酒店的在线评论方式。哪些主题在整个评论中是共同的,哪些术语在每个主题中最相关?当您按评分分离评论时怎么样?一位同事已经为您抓取并预处理了评论,因此您现在的工作是确定评论中的相关主题,并探索其关键术语。评论发现了什么?提示:主题提取对于应对这一挑战非常有帮助。提示 2:连贯性和困惑度是可以帮助您选择有意义数量的主题的指标。 Read reviewsNote: There are two document object columnsDocumentPreprocessed DocumentDocumentPreprocessed Documentgroup by "Rating"View "Rating" distributionright click to open chartsfind kDifferent k values correspond to different models.Collect evaluation metrics for all models.kexplore topicson default labelsadd model idPerplexityTransforming likelihood into perplexity valuesObtain the maximum likelihood of iteration output rowsMerge evaluation indicatorsk = 2 Table Reader Document Viewer Document Viewer GroupBy Bar Chart(JavaScript) Number To String View Exclusivityand Coherence by K Parameter OptimizationLoop Start Loop End GroupBy ConstantValue Column Topic Extractor(Parallel LDA) Topic Scorer (Labs) Topic Explorer View ConstantValue Column Math Formula Top k Row Filter Column Appender Topic Extractor(Parallel LDA) 挑战20:酒店点评主题水平: 硬描述:您在一家旅行社工作,想更好地了解酒店的在线评论方式。哪些主题在整个评论中是共同的,哪些术语在每个主题中最相关?当您按评分分离评论时怎么样?一位同事已经为您抓取并预处理了评论,因此您现在的工作是确定评论中的相关主题,并探索其关键术语。评论发现了什么?提示:主题提取对于应对这一挑战非常有帮助。提示 2:连贯性和困惑度是可以帮助您选择有意义数量的主题的指标。 Read reviewsNote: There are two document object columnsDocumentPreprocessed DocumentDocumentPreprocessed Documentgroup by "Rating"View "Rating" distributionright click to open chartsfind kDifferent k values correspond to different models.Collect evaluation metrics for all models.kexplore topicson default labelsadd model idPerplexityTransforming likelihood into perplexity valuesObtain the maximum likelihood of iteration output rowsMerge evaluation indicatorsk = 2 Table Reader Document Viewer Document Viewer GroupBy Bar Chart(JavaScript) Number To String View Exclusivityand Coherence by K Parameter OptimizationLoop Start Loop End GroupBy ConstantValue Column Topic Extractor(Parallel LDA) Topic Scorer (Labs) Topic Explorer View ConstantValue Column Math Formula Top k Row Filter Column Appender Topic Extractor(Parallel LDA)

Nodes

Extensions

Links