Python新闻等文本情感分析实战【源码分享】

AI看世界

已于 2023-03-19 13:35:40 修改

阅读量2.6k

点赞数 6

分类专栏：副业1 文章标签：机器学习 CNN 文本分类情感分析 Python

于 2023-03-09 17:33:51 首次发布

本文链接：https://blog.csdn.net/qq_42279468/article/details/129427284

版权

副业1 专栏收录该内容

12 篇文章 3 订阅

订阅专栏

1、注：源码放置文末

1.1 环境配置要求：https://blog.csdn.net/qq_42279468/article/details/124987801

2、展示效果：https://www.bilibili.com/video/BV1bP411f7iv/

3、代码

  本项目通过textcnn卷积神经网络实现对文本情感分析识别，由python 3.6.5+Pytorch训练所得。

在这里插入图片描述

3.1 数据集展示

在这里插入图片描述

3.2 模型训练过程

Training and evaluating...
Epoch: 1
Iter:      0, Train Loss:    1.4, Train Acc:  10.94%, Val Loss:    1.4, Val Acc:  13.82%, Time: 0:00:02 *
Iter:    100, Train Loss:    0.8, Train Acc:  70.31%, Val Loss:   0.74, Val Acc:  73.88%, Time: 0:00:33 *
Iter:    200, Train Loss:   0.68, Train Acc:  71.88%, Val Loss:   0.71, Val Acc:  73.88%, Time: 0:01:05 
Iter:    300, Train Loss:   0.68, Train Acc:  75.00%, Val Loss:   0.66, Val Acc:  74.54%, Time: 0:01:37 *
Iter:    400, Train Loss:   0.59, Train Acc:  79.69%, Val Loss:   0.62, Val Acc:  74.97%, Time: 0:02:06 *
Iter:    500, Train Loss:   0.56, Train Acc:  79.69%, Val Loss:    0.6, Val Acc:  76.71%, Time: 0:02:37 *
Iter:    600, Train Loss:   0.64, Train Acc:  78.12%, Val Loss:   0.62, Val Acc:  75.84%, Time: 0:03:08 
Iter:    700, Train Loss:   0.53, Train Acc:  79.69%, Val Loss:   0.57, Val Acc:  79.00%, Time: 0:03:39 *
Iter:    800, Train Loss:   0.67, Train Acc:  76.56%, Val Loss:   0.56, Val Acc:  78.56%, Time: 0:04:08 
Iter:    900, Train Loss:   0.71, Train Acc:  65.62%, Val Loss:   0.54, Val Acc:  78.24%, Time: 0:04:39 
Iter:   1000, Train Loss:   0.64, Train Acc:  68.75%, Val Loss:   0.52, Val Acc:  79.43%, Time: 0:05:10 *
Epoch: 2
Iter:   1100, Train Loss:   0.53, Train Acc:  82.81%, Val Loss:   0.51, Val Acc:  80.74%, Time: 0:05:41 *
Iter:   1200, Train Loss:   0.61, Train Acc:  79.69%, Val Loss:   0.49, Val Acc:  81.94%, Time: 0:06:12 *
Iter:   1300, Train Loss:    0.5, Train Acc:  81.25%, Val Loss:   0.48, Val Acc:  80.85%, Time: 0:06:43 
Iter:   1400, Train Loss:   0.42, Train Acc:  81.25%, Val Loss:   0.46, Val Acc:  82.15%, Time: 0:07:14 *
Iter:   1500, Train Loss:   0.49, Train Acc:  78.12%, Val Loss:   0.46, Val Acc:  81.50%, Time: 0:07:45 
Iter:   1600, Train Loss:   0.43, Train Acc:  81.25%, Val Loss:   0.42, Val Acc:  83.57%, Time: 0:08:16 *
Iter:   1700, Train Loss:   0.42, Train Acc:  84.38%, Val Loss:   0.43, Val Acc:  84.98%, Time: 0:08:47 *
Iter:   1800, Train Loss:   0.37, Train Acc:  84.38%, Val Loss:   0.42, Val Acc:  83.13%, Time: 0:09:18 
Iter:   1900, Train Loss:   0.52, Train Acc:  81.25%, Val Loss:   0.41, Val Acc:  85.20%, Time: 0:09:49 *
Iter:   2000, Train Loss:   0.83, Train Acc:  62.50%, Val Loss:   0.42, Val Acc:  82.26%, Time: 0:10:20 
Iter:   2100, Train Loss:   0.55, Train Acc:  76.56%, Val Loss:    0.4, Val Acc:  86.72%, Time: 0:10:52 *
Epoch: 3
Iter:   2200, Train Loss:    0.4, Train Acc:  84.38%, Val Loss:   0.37, Val Acc:  85.64%, Time: 0:11:22 
Iter:   2300, Train Loss:    0.4, Train Acc:  85.94%, Val Loss:   0.35, Val Acc:  85.09%, Time: 0:11:53 
Iter:   2400, Train Loss:   0.36, Train Acc:  84.38%, Val Loss:   0.33, Val Acc:  88.47%, Time: 0:12:24 *
Iter:   2500, Train Loss:    0.4, Train Acc:  82.81%, Val Loss:   0.36, Val Acc:  86.40%, Time: 0:12:53 
Iter:   2600, Train Loss:   0.43, Train Acc:  81.25%, Val Loss:   0.32, Val Acc:  88.57%, Time: 0:13:24 *
Iter:   2700, Train Loss:    0.4, Train Acc:  82.81%, Val Loss:   0.32, Val Acc:  88.47%, Time: 0:13:56 
Iter:   2800, Train Loss:   0.28, Train Acc:  90.62%, Val Loss:    0.3, Val Acc:  89.12%, Time: 0:14:27 *
Iter:   2900, Train Loss:   0.23, Train Acc:  93.75%, Val Loss:   0.29, Val Acc:  90.10%, Time: 0:14:58 *
Iter:   3000, Train Loss:   0.34, Train Acc:  82.81%, Val Loss:   0.31, Val Acc:  87.92%, Time: 0:15:29 
Iter:   3100, Train Loss:   0.25, Train Acc:  92.19%, Val Loss:   0.29, Val Acc:  90.86%, Time: 0:16:00 *
Iter:   3200, Train Loss:   0.35, Train Acc:  87.50%, Val Loss:   0.26, Val Acc:  90.97%, Time: 0:16:31 *
Epoch: 4
Iter:   3300, Train Loss:   0.26, Train Acc:  92.19%, Val Loss:   0.23, Val Acc:  92.06%, Time: 0:17:02 *
Iter:   3400, Train Loss:   0.32, Train Acc:  89.06%, Val Loss:   0.23, Val Acc:  92.17%, Time: 0:17:33 *
Iter:   3500, Train Loss:   0.22, Train Acc:  92.19%, Val Loss:   0.23, Val Acc:  91.62%, Time: 0:18:04 
Iter:   3600, Train Loss:   0.27, Train Acc:  90.62%, Val Loss:   0.22, Val Acc:  92.27%, Time: 0:18:36 *
Iter:   3700, Train Loss:   0.26, Train Acc:  93.75%, Val Loss:   0.26, Val Acc:  90.97%, Time: 0:19:08 
Iter:   3800, Train Loss:   0.27, Train Acc:  89.06%, Val Loss:   0.23, Val Acc:  92.60%, Time: 0:19:39 *
Iter:   3900, Train Loss:   0.38, Train Acc:  84.38%, Val Loss:    0.2, Val Acc:  92.71%, Time: 0:20:10 *
Iter:   4000, Train Loss:   0.48, Train Acc:  85.94%, Val Loss:   0.19, Val Acc:  93.80%, Time: 0:20:41 *
Iter:   4100, Train Loss:   0.25, Train Acc:  90.62%, Val Loss:   0.22, Val Acc:  92.60%, Time: 0:21:13 
Iter:   4200, Train Loss:   0.19, Train Acc:  92.19%, Val Loss:   0.18, Val Acc:  94.99%, Time: 0:21:44 *
Iter:   4300, Train Loss:   0.27, Train Acc:  90.62%, Val Loss:   0.18, Val Acc:  94.45%, Time: 0:22:15 
Epoch: 5
Iter:   4400, Train Loss:   0.15, Train Acc:  96.88%, Val Loss:   0.15, Val Acc:  95.32%, Time: 0:22:46 *
Iter:   4500, Train Loss:   0.21, Train Acc:  92.19%, Val Loss:   0.18, Val Acc:  93.69%, Time: 0:23:15 
Iter:   4600, Train Loss:   0.11, Train Acc:  96.88%, Val Loss:   0.16, Val Acc:  95.32%, Time: 0:23:47 
Iter:   4700, Train Loss:   0.15, Train Acc:  93.75%, Val Loss:   0.14, Val Acc:  95.21%, Time: 0:24:18 
Iter:   4800, Train Loss:   0.18, Train Acc:  95.31%, Val Loss:   0.15, Val Acc:  95.87%, Time: 0:24:49 *
Iter:   4900, Train Loss:   0.17, Train Acc:  95.31%, Val Loss:   0.17, Val Acc:  94.45%, Time: 0:25:21 
Iter:   5000, Train Loss:   0.24, Train Acc:  92.19%, Val Loss:   0.16, Val Acc:  95.65%, Time: 0:25:52 
Iter:   5100, Train Loss:   0.19, Train Acc:  95.31%, Val Loss:   0.13, Val Acc:  95.87%, Time: 0:26:23 *
Iter:   5200, Train Loss:   0.15, Train Acc:  95.31%, Val Loss:   0.15, Val Acc:  95.32%, Time: 0:26:54 
Iter:   5300, Train Loss:   0.21, Train Acc:  90.62%, Val Loss:   0.14, Val Acc:  96.30%, Time: 0:27:26 *
Epoch: 6
Iter:   5400, Train Loss:   0.13, Train Acc:  95.31%, Val Loss:   0.15, Val Acc:  94.12%, Time: 0:28:02 
Iter:   5500, Train Loss:   0.21, Train Acc:  98.44%, Val Loss:   0.12, Val Acc:  95.97%, Time: 0:28:35 
Iter:   5600, Train Loss:   0.21, Train Acc:  93.75%, Val Loss:   0.16, Val Acc:  94.89%, Time: 0:29:12