Stacking-Based Ensemble Learning of Self-Media Data for Marketing Intention Detection

Abstract

Social network services for self-media, such as Weibo, Blog, and WeChat Public, constitute a powerful medium that allows users to publish posts every day. Due to insufficient information transparency, malicious marketing of the Internet from self-media posts imposes potential harm on society. Therefore, it is necessary to identify news with marketing intentions for life. We follow the idea of text classification to identify marketing intentions. Although there are some current methods to address intention detection, the challenge is how the feature extraction of text reflects semantic information and how to improve the time complexity and space complexity of the recognition model. To this end, this paper proposes a machine learning method to identify marketing intentions from large-scale We-Media data. First, the proposed Latent Semantic Analysis (LSI)-Word2vec model can reflect the semantic features. Second, the decision tree model is simplified by decision tree pruning to save computing resources and reduce the time complexity. Finally, this paper examines the effects of classifier associations and uses the optimal configuration to help people efficiently identify marketing intention. Finally, the detailed experimental evaluation on several metrics shows that our approaches are effective and efficient. The F1 value can be increased by about 5%, and the running time is increased by 20%, which prove that the newly-proposed method can effectively improve the accuracy of marketing news recognition.

Multimodal Marketing Intent Analysis for Effective Targeted Advertising

“…Compared with the existing works, the goal and tasks are distinguishing and fundamentally different. Another set of previous works [21], [22], [23] focus on the detection of marketing content on media platforms. However, their research is coarse-grained and is lack of the comprehensive extraction and the deep analysis of the problem.…”

“…However, their research is coarse-grained and is lack of the comprehensive extraction and the deep analysis of the problem. For example, the problem is coarsely defined as a simple text classification task without image feature involved [21], [22]. Furthermore, none of these studies focus on the analysis of the marketing topics and the extents.…”

“…On the other hand, some works [21], [22], [23] focus on marketing information detection in media platforms. A stacking-based ensemble learning method (SBEL) is proposed to reflect semantic information of texts to identify marketing intent [21]. A graph-based approach (GBA) is proposed to extract the self-defined graph-related and community-related features to detect content marketing articles [22].…”

Detection of Financial Opportunities in Micro-Blogging Data With a Stacked Classification System

“…Thus, automatic knowledge extraction from the comments by experts in financial news, blogs and social media is an interesting research goal and a valuable asset for practical applications [29], [30]. [63], [64]. It has been our intent to exploit the benefits of stacking in ensemble learning techniques to further 160 increase the performance of our system.…”

Physics-Based Feature Makes Machine Learning Cognizing Crystal Properties Simple

“…Stacking is a method of ensemble learning, 22 which consists of the stable base model as a layer of feature extractor, with the base model's predicted values matched to the stacking-feature space (S-F) = {Pred1, Pred2, Pred3, ...}, as can be seen in Figure 3. A logistic regression (LR) model is used as our combiner, and after the LR model adjusts the preferences of all base models, the final predicted value is obtained.…”