search

UUDigitalHumanitieslab / Reader-responses-to-translated-literature

Scripts for the DIOPTRA-L project (Digital Opinions on Translated Literature)
MIT License
0 stars 0 forks source link

Literature review regarding word embeddings #1

Open alexhebing opened 4 years ago

alexhebing commented 4 years ago

The two themes in this project will be:

1) using word embeddings in sentiment analysis. As a starting point, see:

Note that the above two articles were part of the application because they are cited a lot, and were not read extensively (yet)

2) the potential of word embeddings in working multi-lingually. For example:

Task Explore the literature with regard to this themes and cook up a direction to take the project in.

Please note I created an Everhour task to track time on (5% of the total project time - I'll try to come up with a number of hours soon).

alexhebing commented 4 years ago

@BeritJanssen FYI: first set of data available in SurfDrive: '.../DigitalHumanitiesLabatUU/Reader Responses to translated literature/data/initial set (Harry Potter and Dinner)/.

BeritJanssen commented 4 years ago

@alexhebing in the Dinner scrapings, I find this error to occur a lot in the review csv's: 'review_1366787834;https://www.goodreads.com/review/show/1366787834;20510036-the-dinner;English;Aug 17, 2015;Lauren Davis;en;liked it;3;The narrator's voice was wonderfully written -- highly unreliable and with snark to spare. I would have given the book more stars were it not for the implausible set-up. By this I mean: I find it hard to believe that anyone, let alone a highly public politician, would meet at a highly public and terribly posh restaurant to discuss the horrific murder he has just discovered his child, along with that child's cousin, committed. Because the premise struck me as ridiculous, it tainted my view of the The narrator's voice was wonderfully written -- highly unreliable and with snark to spare. I would have given the book more stars were it not for the implausible set-up. By this I mean: I find it hard to believe that anyone, let alone a highly public politician, would meet at a highly public and terribly posh restaurant to discuss the horrific murder he has just discovered his child, along with that child's cousin, committed. Because the premise struck me as ridiculous, it tainted my view of the rest of the book. ...more'

I.e., if you look closely, the text repeats.

alexhebing commented 4 years ago

@BeritJanssen : great catch, many thanks! Moved to its own issue and fixing.

alexhebing commented 4 years ago

I have now done a new scraping and updated the files in SurfDrive (it actually was a lot faster than earlier this week, probably because it is so early in the morning and it's no so busy on the information highway).