Mining and summarizing opinionfeatures in customer reviews
Content          2
Introduction   More & more products are sold on the web, & more    and more people are buying them on the web.   An incr...
   We aim to summarize all the customer reviews of a    product.   We only summarize the features of the product on    w...
Customer reviews                   5
An example summary   The summary looks like the following:   Digital_camera_1:     Feature: picture quality        Posit...
Our task is performed in 3 steps   Step 1: Mining product features that have    been commented on by customers   Step 2:...
Feature-based opinion summarization                               8
Step 1: Mining product feature   The system first downloads all the reviews, and puts them    in the review database.   ...
The proposed techniques                          10
Part of Speech Tagging(POS Tagging)  We use the NLProcessor linguistic parser (NLProcessor   2000), which parses each sen...
    12
13
Upcoming SlideShare
Loading in …5
×

Opinion mining

491 views

Published on

0 Comments
2 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
491
On SlideShare
0
From Embeds
0
Number of Embeds
4
Actions
Shares
0
Downloads
0
Comments
0
Likes
2
Embeds 0
No embeds

No notes for slide

Opinion mining

  1. 1. Mining and summarizing opinionfeatures in customer reviews
  2. 2. Content 2
  3. 3. Introduction More & more products are sold on the web, & more and more people are buying them on the web. An increasing number of people are writing reviews or expressing opinions on the products that they buy. A potential customer reads them to help him/her to make a decision on whether to buy the product. There are additional difficulties because many merchant sites may sell the same product and the manufacture normally produces many kinds of products. 3
  4. 4.  We aim to summarize all the customer reviews of a product. We only summarize the features of the product on which the customers have expressed their opinions and whether the opinions are positive or negative. 4
  5. 5. Customer reviews 5
  6. 6. An example summary The summary looks like the following: Digital_camera_1: Feature: picture quality Positive: 253 <individual review sentences> Negative: 6 <individual review sentences> Feature: size Positive: 134 <individual review sentences> Negative: 10 <individual review sentences> ………… 6
  7. 7. Our task is performed in 3 steps Step 1: Mining product features that have been commented on by customers Step 2: identifying opinion sentences in each review and deciding whether each opinion sentences is positive or nagative Step 3: summarizing the result 7
  8. 8. Feature-based opinion summarization 8
  9. 9. Step 1: Mining product feature The system first downloads all the reviews, and puts them in the review database. How to find out the product features in reviews The features of these sentences are explicitly mentioned , for example:  “The pictures are very clear”  “Overall a fantastic very compact camera” Some features are implicit and hard to find, for example:  “While lifght, it will not easily fit in pockets” We focus on finding features that appear explicitly as nouns/ noun phrases from the reviews. 9
  10. 10. The proposed techniques 10
  11. 11. Part of Speech Tagging(POS Tagging)  We use the NLProcessor linguistic parser (NLProcessor 2000), which parses each sentence the part-of-speech tag of each word (whether the word is a noun, verb, adjective, etc). To show a sentence with the POS tags: <S> <NG><W C=PRP L=SS T=w S=Y> I </W> </NG> <VG> <W C=VBP> am </W><W C=RB> absolutely </W></VG> <W C=IN> in </W> <NG> <W C=NN> awe </W> </NG> <W C=IN> of </W> <NG> <W C=DT> this </W> <W C=NN> camera </W></NG><W C=.> . </W></S> 11
  12. 12.  12
  13. 13. 13

×