label is positive and sentiscore is in negative

sukh
sukh New Altair Community Member
edited November 2024 in Community Q&A
Hi all,
i am working with sentiment analysis. for that i am using IMDb data set which has two directories one for positive and another one is for negative which further consists text files in each directory. these text files are used for training . but the problem arises when the result comes.
As in results for text files fall in positive directory get the sentiment score as negative.

like  label          Sentiscore      document id
        positive        -0.076            1
        negative        0.34              2

how we can say, whether the document is positive or negative?? 

Thanks ans Regards:
Sukh
Tagged:

Answers

  • Andrew2
    Andrew2 New Altair Community Member
    Hello

    Do you know how the positive and negative sentiments were assigned to the documents in the first place? Do you have any reason to think that a sentiment calculated by you would match the original sentiment?

    regards

    Andrew
  • sukh
    sukh New Altair Community Member
    Sir, i have used a standard dataset downloaded from:

    http://www.cs.cornell.edu/people/pabo/movie-review-data/


    polarity dataset v2.0 ( 3.0Mb) (includes README v2.0): 1000 positive and 1000 negative processed reviews. Introduced in Pang/Lee ACL 2004. Released June 2004.


    i have used this dataset,
    Thanks ans Regards:
    Sukh
  • Andrew2
    Andrew2 New Altair Community Member
    The dataset is marked as positive or negative based on analysis of stars given by people. I would be amazed if sentiment analysis based on words would give the same result.
  • sukh
    sukh New Altair Community Member
    Actually if the label is negative then why the magnitude of sentiment comes in positive and vice versa. I could not figure out this.
    Regards:
    Sukh