• Aucun résultat trouvé

Sentiment Analysis of Twitter Messages: Tasks, Approaches and Results

N/A
N/A
Protected

Academic year: 2022

Partager "Sentiment Analysis of Twitter Messages: Tasks, Approaches and Results"

Copied!
1
0
0

Texte intégral

(1)

Sentiment Analysis of Twitter Messages: Tasks, Approaches and Results

Natalia Loukachevitch

Research Computing Center, Moscow State University, Russia

Abstract. Microblog messages became a very popular tool for commu- nication between people. Authors of the messages write about their life, convey their opinions on various topics including political and religious views, products and services, etc. Thus, microblogging sites as Twitter become valuable sources of information about peoples’s opinions and sen- timents. Approaches for extracting these opinions and their aggregation are actively studied.

In my talk I consider sentiment analysis tasks proposed for processing Twitter messages and the existing approaches including neural networks, which allowed improving the existing results during last year. Also I present results of the Russian evaluation of sentiment analysis systems (SentiRuEval) organized in 2015-2016.

Keywords: sentiments analysis, microblog messages, opinion mining

References

1. Loukachevitch, N.V., Rubtsova, Y.: Entity-oriented sentiment analysis of tweets:

Results and problems. In: Text, Speech, and Dialogue - 18th International Confer- ence, TSD 2015, Pilsen,Czech Republic, September 14-17, 2015, Proceedings. (2015) 551–559

2. Loukachevitch, N., Blinov, P., Kotelnikov, E., Rubtsova, Y., Ivanov, V., V, V., Tutubalina, E.: Sentirueval: testing object-oriented sentiment analysis systems in russian. In: Proceedings of International Conference Dialog. Volume 2. (2015) 3–13

Références

Documents relatifs

This vocabulary can be used to query opinions and emotions about financial institutions and stock values across different web sites and information sources.. The main advantage of

We propose a methodology that provides statistically significant estimates of sentiment category proportions in social science, and in particular in the Microblogging Retrieval that

To take changes over time into account, we develop a novel time series analysis approach that first derives word frequency time series from sets of tweets and then performs

With respect to these applications, where a first analysis is performed to discrim- inate between relevant and irrelevant tweets, limiting the collection of tweets to those posted

Our approach extracts the contextual semantics of words and uses them to update the words’ prior sentiment orientations and/or strength in a given sentiment lexicon. The evaluation

To evaluate our approach, we perform binary sentiment classification (positive / negative classification of tweets) using a MaxEnt classifier and observe fluctuations (increases

Ranking Algorithm RA-SR In this approach we use a method named RA-SR (using Ranking Algorithms to build Sentiment Resources) [7], which produces sentiment inventories based

In this article, we describe some results obtained from the synthesis of Social Network Analysis and Sentiment Analysis applied to the channel #SamSmith during the Grammy Awards