Mining and summarizing customer reviews
read more
Citations
Convolutional Neural Networks for Sentence Classification
Convolutional Neural Networks for Sentence Classification
Opinion Mining and Sentiment Analysis
Representation Learning with Contrastive Predictive Coding
Sentiment Analysis and Opinion Mining
References
WordNet : an electronic lexical database
Fast Algorithms for Mining Association Rules in Large Databases
Foundations of Statistical Natural Language Processing
Thumbs up? Sentiment Classiflcation using Machine Learning Techniques
Thumbs up? Sentiment Classification using Machine Learning Techniques
Related Papers (5)
Frequently Asked Questions (10)
Q2. What are the future works in "Mining and summarizing customer reviews" ?
In their future work, the authors plan to further improve and refine their techniques, and to deal with the outstanding problems identified above, i. e., pronoun resolution, determining the strength of opinions, and investigating opinions expressed with adverbs, verbs and nouns. Finally, the authors will also look into monitoring of customer reviews. The authors believe that monitoring will be particularly useful to product manufacturers because they want to know any new positive or negative comments on their products whenever they are available. Although a new review may be added, it may not contain any new information.
Q3. What is the key step in the process of finding the features of a product?
Since their system aims to find what people like and dislike about a given product, how to find the product features that people talk about is the crucial step.
Q4. What are the two techniques for finding the key features of a term?
In terminology finding, there are basically two techniques for discovering terms in corpora: symbolic approaches that rely on syntactic description of terms, namely noun phrases, and statistical approaches that exploit the fact that the words composing a term tend to be found close to each other and reoccurring [21, 22, 7, 6].
Q5. how to add adverbs with orientation to seed list?
Every time an adjective with its orientation is added to the seed list, the seed list is updated; therefore calling OrientationSearch repeatedly is necessary in order to exploit the newly added information.
Q6. How many positive and negative reviews do you get?
There are 253 customer reviews that express positive opinions about the picture quality, and only 6 that express negative opinions.
Q7. What does Cardie et al propose to do?
They propose to use opinion-oriented “scenario templates” to act as summary representations of the opinions expressed in a document, or a set of documents.
Q8. what is the orientation of an opinion sentence?
The opinion words are mostly either positive or negative, e.g., there are two positive opinion words, good and exceptional in “overall this is a good camera with a really good picture clarity & an exceptional close-up shooting capability.
Q9. What is the procedure for predicting the orientation of adjectives?
Procedure OrientationPrediction takes the adjective seed list and a set of opinion words whose orientations need to be determined.(→ = similarity; = antonymy)
Q10. What is the procedure used to extract infrequent features?
The authors extract infrequent features using the procedure in Figure 6:The authors use the nearest noun/noun phrase as the noun/noun phrase that the opinion word modifies because that is what happens most of the time.