Q6 – Please comment on anything else you noticed. (There was no Likart scale.) Summary All comments were positive and neutral in this final section. Four plagiarism comments and one fake news comment were also in here (and have been moved), showing it is useful to have a general question at the end to pick Continue Reading
What emotions did people feel using the text generator?
After the experiments, Question 2 was “I felt emotional when the generated text appeared. Which emotions did you feel, please describe?” Summary Two thirds of people (64%) were emotionally involved in their text generation experiments. Many emotions were raised. A third (36%) professed no emotion, or indicated none but added a named feeling. Of the Continue Reading
Word processor with added text generator
After the experiments, Question 4 was “Do you think you would use this, or a similar feature, in an ideas editor or word processor? Extra features?” Summary Likart median score was 3, Neutral (actually, balanced). The data shows that this polarised opinion, with positive only slightly more than negative, and few neutrals. There were no Continue Reading
Did people enjoy using the text generator?
After the three experiments, people were first asked two related questions. Question 1 “Enjoyment (what was Most and Least enjoyable)”. Summary People most liked the stimulation of a responsive ideas generator, rather than expecting the system to actually write coherent relevant text. The ‘least interesting’ question produced more specific replies, and specific complaints about the Continue Reading
Ownership and Plagiarism of generated texts
Two of the questions after the text generation experiments dealt with ownership of the text. Do you feel that you have used somebody else’s work? [Likart scale 1-5, Strongly Agree, Agree… Strongly Disagree] Does this seem relevant and why? Do you think you could sell this as your own work? [Likart scale 1-5] Do you Continue Reading
Edit generated text or not? That is the question
Index of AI research Summary The writing task involved generating text and then copying it into a text editor for rewriting, to create a hybrid work. The text generator allowed repeats but no actual fine editing. So by observing what happened in the editing window, it was possible to see if any editing had taken place. Continue Reading
Tower of Doom part 2: The Bloody Tale
Episode 2 of the Tower of Doom. Any horror/death related texts will be in this series. You have been warned. Although they are pretty innocuous. See also Tower of Doom 1: The Distant Shout of the Great Storm. This is not part of the classic literature series. I am generating text from short phrases that I Continue Reading
A Mountain of Pent Up Tears – children’s stories generated texts
Children’s stories – this is part of the classic literature series on this blog, experiments in hybrid fiction. I turned out so fast, I barely looked back. (I turned to look, only to find the figure had gone.) What has gone before was the dark room. In the far left corner lay a pile of Continue Reading
Sentiment Analysis of Caption, News and Fiction text generation experiments
From: text generation editor research (UAL London 2020 see credits). What happens when writers use a computer text generator to write articles, giving them only an image prompt. Go to Index of AI research Sentiment Analysis The Study had three text generation and editing tasks, to make a Caption, a News article, and a Fiction Continue Reading
All the Rubbish of a Great City – classic literature vs text generation
From the series of classic literature vs the future… All The Rubbish of a Great City Part 1: No Sun Ever Since That Day Dear Farewell You may be glad to see your letter of 6th April last from me. You are still in the good humour of the last time, and I Continue Reading