# Senti17 at SemEval-2017 Task 4: Ten Convolutional Neural Network Voters for Tweet Polarity Classification

## TL;DR

This paper introduces Senti17, a tweet sentiment classification system using ten convolutional neural networks with different initializations, combined through majority voting, achieving competitive results in SemEval-2017.

## Contribution

The novel approach employs multiple ConvNets with different initializations and combines their outputs for improved tweet sentiment classification.

## Key findings

- Achieved 67.4% accuracy in SemEval-2017 Task 4
- Ranked fourth among 38 systems
- Demonstrated effectiveness of ensemble ConvNet approach

## Abstract

This paper presents Senti17 system which uses ten convolutional neural networks (ConvNet) to assign a sentiment label to a tweet. The network consists of a convolutional layer followed by a fully-connected layer and a Softmax on top. Ten instances of this network are initialized with the same word embeddings as inputs but with different initializations for the network weights. We combine the results of all instances by selecting the sentiment label given by the majority of the ten voters. This system is ranked fourth in SemEval-2017 Task4 over 38 systems with 67.4%