RECORD
CompText: Visualizing, Comparing & Understanding Text Corpus
Computation and Language · Submitted 27 Jul 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim There are multiple existing texts comparing methods present that compare topics rather than sentiments but we feel that focusing on sentiment-carrying words would better compare the two corpora.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
A common practice in Natural Language Processing (NLP) is to visualize the text corpus without reading through the entire literature, still grasping the central idea and key points described. For a long time, researchers focused on extracting topics from the text and visualizing them based on their relative significance in the corpus. However, recently, researchers started coming up with more complex systems that not only expose the topics of the corpus but also word closely related to the topic to give users a holistic view. These detailed visualizations spawned research on comparing text corpora based on their visualization. Topics are often compared to idealize the difference between corpora. However, to capture greater semantics from different corpora, researchers have started to compare texts based on the sentiment of the topics related to the text. Comparing the words carrying the most weightage, we can get an idea about the important topics for corpus. There are multiple existing texts comparing methods present that compare topics rather than sentiments but we feel that focusing on sentiment-carrying words would better compare the two corpora. Since only sentiments can explain the real feeling of the text and not just the topic, topics without sentiments are just nouns. We aim to differentiate the corpus with a focus on sentiment, as opposed to comparing all the words appearing in the two corpora. The rationale behind this is, that the two corpora do not many have identical words for side-by-side comparison, so comparing the sentiment words gives us an idea of how the corpora are appealing to the emotions of the reader. We can argue that the entropy or the unexpectedness and divergence of topics should also be of importance and help us to identify key pivot points and the importance of certain topics in the corpus alongside relative sentiment.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | A common practice in Natural Language Processing (NLP) is to visualize the text corpus without reading through the entire literature, still grasping the central idea and key points described. | background 1.00 | 0.04 | 0.03 | asserted 1.00 |
| s1 | For a long time, researchers focused on extracting topics from the text and visualizing them based on their relative significance in the corpus. | background 1.00 | 0.03 | 0.02 | asserted 1.00 |
| s2 | However, recently, researchers started coming up with more complex systems that not only expose the topics of the corpus but also word closely related to the topic to give users a holistic view. | background 0.99 | 0.04 | 0.04 | asserted 1.00 |
| s3 | These detailed visualizations spawned research on comparing text corpora based on their visualization. | background 1.00 | 0.05 | 0.04 | asserted 1.00 |
| s4 | Topics are often compared to idealize the difference between corpora. | background 0.99 | 0.05 | 0.03 | asserted 0.97 |
| s5 | However, to capture greater semantics from different corpora, researchers have started to compare texts based on the sentiment of the topics related to the text. | background 0.89 | 0.06 | 0.11 | asserted 0.97 |
| s6 | Comparing the words carrying the most weightage, we can get an idea about the important topics for corpus. | background 0.62 | 0.12 | 0.06 | hedged possibility 0.60 |
| s7 | There are multiple existing texts comparing methods present that compare topics rather than sentiments but we feel that focusing on sentiment-carrying words would better compare the two corpora. | gap 0.89 | 0.10 | 0.21 | asserted 0.56 |
| s8 | Since only sentiments can explain the real feeling of the text and not just the topic, topics without sentiments are just nouns. | gap 0.32 | 0.09 | 0.13 | asserted 1.00 |
| s9 | We aim to differentiate the corpus with a focus on sentiment, as opposed to comparing all the words appearing in the two corpora. | contribution 0.99 | 0.24 | 0.25 | asserted 0.93 |
| s10 | The rationale behind this is, that the two corpora do not many have identical words for side-by-side comparison, so comparing the sentiment words gives us an idea of how the corpora are appealing to the emotions of the reader. | contribution 0.41 | 0.17 | 0.13 | asserted 0.66 |
| s11 | We can argue that the entropy or the unexpectedness and divergence of topics should also be of importance and help us to identify key pivot points and the importance of certain topics in the corpus alongside relative sentiment. | future work 0.48 | 0.10 | 0.12 | hedged possibility 0.66 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
A common practice in Natural Language Processing (NLP) is to visualize the text corpus without reading through the entire literature, still grasping the central idea and key points described. For a long time, researchers focused on extracting topics from the text and visualizing them based on their relative significance in the corpus. However, recently, researchers started coming up with more complex systems that not only expose the topics of the corpus but also word closely related to the topic to give users a holistic view. These detailed visualizations spawned research on comparing text corpora based on their visualization. Topics are often compared to idealize the difference between corpora. However, to capture greater semantics from different corpora, researchers have started to compare texts based on the sentiment of the topics related to the text. Comparing the words carrying the most weightage, we can get an idea about the important topics for corpus. There are multiple existing texts comparing methods present that compare topics rather than sentiments but we feel that focusing on sentiment-carrying words would better compare the two corpora. Since only sentiments can explain the real feeling of the text and not just the topic, topics without sentiments are just nouns. We aim to differentiate the corpus with a focus on sentiment, as opposed to comparing all the words appearing in the two corpora. The rationale behind this is, that the two corpora do not many have identical words for side-by-side comparison, so comparing the sentiment words gives us an idea of how the corpora are appealing to the emotions of the reader. We can argue that the entropy or the unexpectedness and divergence of topics should also be of importance and help us to identify key pivot points and the importance of certain topics in the corpus alongside relative sentiment.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.