GenSumm: A Joint Framework for Multi-task Tweet Classification and Summarization using Sentiment Analysis and Generative Modelling

Author(s):  
Diksha Bansal ◽  
Rahul Grover ◽  
Naveen Saini ◽  
Sriparna Saha
2019 ◽  
Vol 3 (4) ◽  
pp. 405
Author(s):  
Cahyo Prianto ◽  
Nisa Hanum Harani ◽  
Indra Firmansyah

The development of technology today has been growing rapidly and has an impact on the behavior patterns of people who feel it. The Ministry of Communication and Information (KOMINFO) released a data that of 265 million people of Indonesia, there are around 54% have used internet technology or about 143 million people. In one survey IDN Research Institute said that there are three Social Media that are widely used in Indonesia, namely Facebook, Instagram and Twitter. This study focuses on extracting data in the form of text produced from social media twitter that responds to the account of the RI presidential candidates in the 2019 elections. Sentiment analysis is obtained through tweet classification using sentiment analysis tools such as NRC Lexicon and Bing Lexicon so that information is obtained in the form of positive polarity and negative polarity from community tweets towards the Presidential candidates in the 2019 elections. Using March data before the 2019 election, for candidate 01 Joko Widodo, the NRC Lexicon analysis gave a value of 249 and bing lexicon of 267 with an average value of 0.11, while for candidate 02 Prabowo Subianto the NRC Lexicon analysis gave a value of 195 and bing lexicon of 204 with an average value of 0.085. Using april data after the 2019 election. Candidate 01 Joko Widodo still received a lot of responses from netizens but the sentiment value shifted more negatively compared to candidate 02 Prabowo Subianto. For candidate 01 Joko Widodo the NRC Lexicon analysis gave a value of 17 and bing lexicon of -273 with an average value of -0,246, while for candidate 02 Prabowo Subianto the NRC Lexicon analysis gave a value of 238 and bing lexicon of -73 with an average value of -0.02430939.


Author(s):  
Agung Eddy Suryo Saputro ◽  
Khairil Anwar Notodiputro ◽  
Indahwati A

In 2018, Indonesia implemented a Governor's Election which included 17 provinces. For several months before the Election, news and opinions regarding the Governor's Election were often trending topics on Twitter. This study aims to describe the results of sentiment mining and determine the best method for predicting sentiment classes. Sentiment mining is based on Lexicon. While the methods used for sentiment analysis are Naive Bayes and C5.0. The results showed that the percentage of positive sentiment in 17 provinces was greater than the negative and neutral sentiments. In addition, method C5.0 produces a better prediction than Naive Bayes.


Corpora ◽  
2019 ◽  
Vol 14 (3) ◽  
pp. 327-349
Author(s):  
Craig Frayne

This study uses the two largest available American English language corpora, Google Books and the Corpus of Historical American English (coha), to investigate relations between ecology and language. The paper introduces ecolinguistics as a promising theme for corpus research. While some previous ecolinguistic research has used corpus approaches, there is a case to be made for quantitative methods that draw on larger datasets. Building on other corpus studies that have made connections between language use and environmental change, this paper investigates whether linguistic references to other species have changed in the past two centuries and, if so, how. The methodology consists of two main parts: an examination of the frequency of common names of species followed by aspect-level sentiment analysis of concordance lines. Results point to both opportunities and challenges associated with applying corpus methods to ecolinguistc research.


Sign in / Sign up

Export Citation Format

Share Document