Implicit dimension identification in user-generated text with LSTM networks

Abstract

In the process of online storytelling, individual users create and consume highly diverse content that contains a great deal of implicit beliefs and not plainly expressed narrative.It is hard to manually detect these implicit beliefs, intentions and moral foundations of the writers.We study and investigate two different tasks, each of which reflect the difficulty of detecting an implicit user's knowledge, intent or belief that may be based on writer's moral foundation: 1) political perspective detection in news articles 2) identification of informational vs. conversational questions in community question answering (CQA) archives and. In both tasks we first describe new interesting annotated datasets and make the datasets publicly available. Second, we compare various classification algorithms, and show the differences in their performance on both tasks. Third, in political perspective detection task we utilize a narrative representation language of local press to identify perspective differences between presumably neutral American and British press.

A Complete Process of Text Classification System Using State-of-the-Art NLP Models

“…Comprising three gates: input, forget, and output gates, taking a combination of these three gates, it determines the hidden state [ 22 ]. The applications based on RNN and LSTM have been used in solving many NLP problems due to their capacity of capturing complex patterns within the text [ 140 ]. It has also been used in sequence labeling tasks in POS (part of speech) activity.…”

Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet

“…To train the model we used a dataset of 25,000 articles (Makarenkov et al, 2019a) which are covering the conflict from both the Israeli and Arab online media. The articles from the Israeli media were given an Israeli-perspective label, and the articles from the Arab media sources were given a Palestinian-perspective label.…”

IR3218-UI at SemEval-2020 Task 12: Emoji Effects on Offensive Language IdentifiCation

“…Their results showed that LSTM outperformed other models with 93.48% accuracy. LSTM was also used by Makarenkov et al (2019) for political perspective identification in online news articles. They experimented using various hyper-parameter setting for the LSTM network such as word embedding source, memory size, word cutoff and batch size.…”

“…Based on the previous description, in this study, we want to identify offensive language on Twitter using LSTM as the model classification. LSTM was used as the model classification since it showed good performance in text classification task based on the study done by Xiao et al (2018) and Makarenkov et al (2019). Based on the study of Singh et al (2019), we want to implement the same strategy in order to study the effect of emojis on offensive language identification.…”