融合标题情感和话题特征的新闻推荐算法

doi:10.3969/j.issn.0255-8297.2024.05.008

摘要/Abstract

摘要： 文本是新闻最主要的媒介，传统基于情感词典的新闻推荐算法在分析情感词汇时，通常会忽略词典外的词汇情感，使得情感词汇标记不全，导致预测准确度不高和排序性能不佳等问题。针对这些问题，提出了一种推断未知词汇情感的启发式方法，设计了一种对应的新闻推荐算法来验证其有效性。构建标题-情感词-情感字三部图模型，将情感词典中的词汇情感扩散到单个的字，通过情感词和情感字得到了标题情感。首先，用词袋模型提取出标题的话题特征。然后，计算标题之间的情感相似度和话题相似度，并将两种相似度融合作为综合的相似度评价指标。接着，选取与目标新闻相似度较高的新闻作为邻居。算法通过邻居新闻的时均点击量，预测出目标新闻的时均点击量，将时均点击量视为目标新闻的预测评分，最终将评分排序实现对用户的新闻推荐。在真实的网易热榜新闻数据集上验证了该方法的可行性与有效性。对比其他算法，本文算法的平均绝对误差最优准确度提升了2.2%~3.4%，均方根误差最优准确度提升了2.3%~2.9%，归一化折损累计增益平均得分提升了0.7%~1.8%。

关键词: 推荐系统, 情感分析, 词袋, 协同过滤, 三部图

Abstract: Traditional lexicon-based news recommendation algorithms often ignore the emotional nuances present in words beyond the confines of the dictionary. This oversight can lead to issues such as diminished prediction accuracy and subpar sorting performance. To address these challenges, this paper introduces a heuristic approach to deduce the sentiment of unfamiliar words and devises a news recommendation algorithm to verify its feasibility. A tripartite graph model is constructed to propagate sentiment from a sentiment dictionary to individual words and obtain the headline sentiment. In addition, the bag-of-words model is used to extract topic features from the headlines. The sentiment similarity and topic similarity between headlines are calculated, consolidating these into a comprehensive similarity evaluation index. The news with higher similarity to the target news is then selected as the neighbor. The algorithm predicts the hourly average click volume of the target news by considering the hourly average click volume of neighbors, treating this as the predicted score for the target news. Finally, users receive a selection of high-scoring news articles. Validation using real data from NetEase News confirms the feasibility and effectiveness of our algorithm. Compared with other algorithms, our algorithm has shown improvements in the optimal accuracy of mean absolute error (MAE) by 2.2% to 3.4%, root mean square error (RMSE) by 2.3% to 2.9%, and the mean score of normalized discounted cumulative gain (NDCG) by 0.7% to 1.8%, respectively.

Key words: recommender system, sentiment analysis, bag-of-words, collaborative filtering, tripartite graph

中图分类号:

TP391

艾均, 洪星琦. 融合标题情感和话题特征的新闻推荐算法[J]. 应用科学学报, 2024, 42(5): 810-822.

AI Jun, HONG Xingqi. News Recommendation Algorithm Incorporating Headline Sentiment and Topic Characteristics[J]. Journal of Applied Sciences, 2024, 42(5): 810-822.

参考文献

[1] Parizi A H, Kazemifard M. Emotional news recommender system [C]//6th International Conference of Cognitive Science (ICCS), 2016: 37-41.
[2] Kunaver M, Požrl T. Diversity in recommender systems-a survey [J]. Knowledge-Based Systems, 2017, 123: 154-162.
[3] Li L, Wang D D, Zhu S Z, et al. Personalized news recommendation: a review and an experimental investigation [J]. Journal of Computer Science and Technology, 2011, 26(5): 754- 766.
[4] Liu B. Sentiment analysis and opinion mining [M]. Cham: Springer, 2012.
[5] Pang B, Lee L. Opinion mining and sentiment analysis [J]. Foundations and Trends in Information Retrieval, 2008, 2(1/2): 1-135.
[6] Medhat W, Hassan A, Korashy H. Sentiment analysis algorithms and applications: a survey [J]. Ain Shams Engineering Journal, 2014, 5(4): 1093-1113.
[7] Batrinca B, Treleaven P C. Social media analytics: a survey of techniques, tools and platforms [J]. Ai & Society, 2015, 30(1): 89-116.
[8] Wu C, Wu F, Qi T, et al. SentiRec: sentiment diversity-aware neural news recommendation [C]//1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2020: 44-53.
[9] Dang C N, Moreno-García M N, Prieta F D. An approach to integrating sentiment analysis into recommender systems [J]. Sensors (Basel, Switzerland), 2021, 21(16): 5666.
[10] Raza S, Ding C. News recommender system considering temporal dynamics and news taxonomy [C]//IEEE International Conference on Big Data, 2020: 920-929.
[11] Kumar S, De K, Roy P P. Movie recommendation system using sentiment analysis from microblogging data [J]. IEEE Transactions on Computational Social Systems.IEEE, 2020, 7(4): 915-923.
[12] Hutto C, Gilbert E. VADER: a parsimonious rule-based model for sentiment analysis of social media text [C]//International AAAI Conference on Web and Social Media, 2014, 8(1): 216-225.
[13] Zucco C, Calabrese B, Agapito G, et al. Sentiment analysis for mining texts and social networks data: methods and tools [J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2020, 10(1): e1333.
[14] Van Atteveldt W, Van Der Velden M A C G, Boukes M. The validity of sentiment analysis: comparing manual annotation, crowd-coding, dictionary approaches, and machine learning algorithms [J]. Communication Methods and Measures, 2021, 15(2): 121-140.
[15] Patankar A, Bose J, Khanna H. A bias aware news recommendation system [C]//2019 IEEE 13th International Conference on Semantic Computing (ICSC), 2019: 232-238.
[16] Xu L, Lin H, Pan Y, et al. Constructing the affective lexicon ontology [J]. Journal of the China Society for Scientific and Technical Information, 2008, 27(2): 180-185.
[17] Qader W A, Ameen M M, Ahmed B I. An overview of bag of words; importance, implementation, applications, and challenges [C]//2019 International Engineering Conference (IEC), 2019: 200-204.
[18] 李晨, 朱世伟, 魏墨济, 等. 基于词典与规则的新闻文本情感倾向性分析[J]. 山东科学, 2017, 30(1): 115-121. Li C, Zhu S W, Wei M J, et al. Lexicon and rules based news text sentiment analysis [J]. Shandong Science, 2017, 30(1): 115-121. (in Chinese)
[19] Zahrotun L. Comparison jaccard similarity, cosine similarity and combined both of the data clustering with shared nearest neighbor method [J]. Computer Engineering and Applications Journal, 2016, 5(1): 11-18.
[20] Salton G, Buckley C. Term-weighting approaches in automatic text retrieval [J]. Information Processing & Management, 1988, 24(5): 513-523.
[21] Wu F Z, Qiao Y, Chen J H, et al. MIND: a large-scale dataset for news recommendation [C]//58th Annual Meeting of the Association for Computational Linguistics, 2020: 3597-3606.
[22] Willmott C J, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance [J]. Climate Research, 2005, 30: 79-82.
[23] Chai T, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE)?—arguments against avoiding RMSE in the literature [J]. Geoscientific Model Development, 2014, 7(3): 1247-1250.
[24] Wang Y N, Wang L W, Li Y Z, et al. A theoretical analysis of NDCG type ranking measures [J]. 26th Annual Conference on Learning Theory, 2013: 1-30.
[25] Qi T, Wu F, Wu C, et al. PP-rec: news recommendation with personalized user interest and time-aware news popularity [DB/OL]. 2021[2022-07-14]. http://arxiv.org/abs/2106.01300.