在數位媒體主導的時代中，網路新聞對公眾意見具有深遠的影響。然而，
帶有固有媒體偏見的報導可能會扭曲公眾對事件的理解。本論文介紹了
時間感知媒體偏見（TAMB）模型，這是一種輕量化且具時間敏感性的方
法，旨在評估新聞報導中的媒體偏見。本研究聚焦於不同媒體對「高端疫
苗」的報導立場，將文章分類為支持、中立或反對立場，解決了大型語言
模型面臨的數據稀缺問題。對於新的議題的資料集，TAMB 的適應性允
許及時更新，對於快速變化的新聞周期至關重要，並在標記數據集有限的
情境中在立場檢測任務上有顯著進步。

In an era dominated by digital media, online news heavily influences public opinion. However, reports imbued with inherent media bias can distort public understanding of events. This thesis introduces the Time-Aware
Media Bias (TAMB) model, a lightweight and time-sensitive approach designed to assess media bias in news reporting. Focusing on the portrayal
of “Medigen Vaccine” by various outlets, the model categorizes articles
into supportive, neutral, or opposing stances, addressing the scarcity of
data that challenges large language models. For datasets on new topics,
the adaptability of TAMB allows for timely updates in the rapidly evolving news cycle, demonstrating significant advancements in stance detection
tasks within contexts constrained by limited labeled datasets.

[1] J. Dunaway, K. Searles, M. Sui, and N. Paul, “News Attention in a Mobile Era,” Journal of ComputerMediated Communication, vol. 23, pp. 107–124, 03 2018.
[2] S. Vosoughi, D. Roy, and S. Aral, “The spread of true and false news online,” science, vol. 359, no. 6380, pp. 1146–1151, 2018.
[3] S. Bradshaw, H. Bailey, and P. N. Howard, Industrialized disinformation: 2020 global inventory of organized social media manipulation. Computational Propaganda Project at the Oxford Internet Institute, 2021.
[4] C. W. Sies and J. Brooker, “Could these be gallstones?,” The Lancet, vol. 365, p. 1388, Apr 2005.
[5] H. Allcott and M. Gentzkow, “Social media and fake news in the 2016 election,” The Journal of Economic Perspectives, vol. 31, no. 2, pp. 211–235, 2017.
[6] Z. Reich, “Comparing news reporting across print, radio, television and online,” Journalism Studies, vol. 17, pp. 1–21, 02 2015.
[7] S. L. Evans, R. Jones, E. Alkan, J. S. Sichman, A. Haque, F. B. S. de Oliveira, D. Mougouei, et al.,“The emotional impact of covid-19 news reporting: A longitudinal study using natural language processing,” Human Behavior and Emerging Technologies, vol. 2023, 2023.
[8] Cheng-Shan Liu, “Political science: Media influence you may not know about,” 2022.
[9] A. AlDayel and W. Magdy, “Stance detection on social media: State of the art and trends,” Information Processing & Management, vol. 58, no. 4, p. 102597, 2021.
[10] D. Küçük and F. Can, “Stance detection: A survey,” ACM Computing Surveys (CSUR), vol. 53, no. 1,pp. 1–37, 2020.
[11] H. Wang, J. Li, H. Wu, E. Hovy, and Y. Sun, “Pre-trained language models and their applications,”Engineering, 2022.
[12] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
[13] L. Lin, Reuters Institute Digital News Report 2021. Reuters Institute for the Study of Journalism, 2021.
[14] I. N. Tools, “Taiwan’s disinformation,”
[15] Y.-H. Lu, C.-Y. Li, and Z.-W. Lin, “The taiwan ai labs hakka asr system for formosa speech recognition challenge 2023,” in Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023), pp. 403–408, 2023.
[16] M. McCombs, “A look at agenda-setting: Past, present and future,” Journalism studies, vol. 6, no. 4, pp. 543–557, 2005.
[17] L. Cheng-Shan, What you may not know media influence. Science Development Monthly, 2012.
[18] S. Mohammad, S. Kiritchenko, P. Sobhani, X. Zhu, and C. Cherry, “Semeval-2016 task 6: Detecting stance in tweets,” in Proceedings of the 10th international workshop on semantic evaluation (SemEval2016), pp. 31–41, 2016.
[19] K. Glandt, S. Khanal, Y. Li, D. Caragea, and C. Caragea, “Stance detection in covid-19 tweets,” in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Long Papers), vol. 1, 2021.
[20] G. Zarrella and A. Marsh, “Mitre at semeval-2016 task 6: Transfer learning for stance detection,”arXiv preprint arXiv:1606.03784, 2016.
[21] P. Vijayaraghavan, I. Sysoev, S. Vosoughi, and D. Roy, “Deepstance at semeval-2016 task 6: Detecting stance in tweets using character and word-level cnns,” arXiv preprint arXiv:1606.05694, 2016.
[22] M. Umer, Z. Imtiaz, S. Ullah, A. Mehmood, G. S. Choi, and B.-W. On, “Fake news stance detection using deep learning architecture (cnn-lstm),” IEEE Access, vol. 8, pp. 156695–156706, 2020.
[23] K. Dey, R. Shrivastava, and S. Kaushik, “Topical stance detection for twitter: A two-phase lstm model using attention,” in Advances in Information Retrieval: 40th European Conference on IR Research, ECIR 2018, Grenoble, France, March 26-29, 2018, Proceedings 40, pp. 529–536, Springer, 2018.
[24] E. Kochkina, M. Liakata, and I. Augenstein, “Turing at semeval-2017 task 8: Sequential approach to rumour stance classification with branch-lstm,” arXiv preprint arXiv:1704.07221, 2017.
[25] A. Rashed, M. Kutlu, K. Darwish, T. Elsayed, and C. Bayrak, “Embeddings-based clustering for target specific stances: The case of a polarized turkey,” in Proceedings of the International AAAI Conference on web and social media, vol. 15, pp. 537–548, 2021.
[26] Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, and R. Soricut, “Albert: A lite bert for selfsupervised learning of language representations,” arXiv preprint arXiv:1909.11942, 2019.
[27] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, “Roberta: A robustly optimized bert pretraining approach,” arXiv preprint arXiv:1907.11692, 2019.
[28] Y. Cui, W. Che, T. Liu, B. Qin, S. Wang, and G. Hu, “Revisiting pre-trained models for chinese natural language processing,” arXiv preprint arXiv:2004.13922, 2020.
[29] Y. Sun, S. Wang, Y. Li, S. Feng, X. Chen, H. Zhang, X. Tian, D. Zhu, H. Tian, and H. Wu, “Ernie: Enhanced representation through knowledge integration,” arXiv preprint arXiv:1904.09223, 2019.
[30] N. Reimers and I. Gurevych, “Sentence-bert: Sentence embeddings using siamese bert-networks,” arXiv preprint arXiv:1908.10084, 2019.
[31] K. Shu, S. Wang, and H. Liu, “Understanding user profiles on social media for fake news detection,” in 2018 IEEE conference on multimedia information processing and retrieval (MIPR), pp. 430–435, IEEE, 2018.
[32] S. Shi, K. Qiao, J. Chen, S. Yang, J. Yang, B. Song, L. Wang, and B. Yan, “Mgtab: A multi-relational graph-based twitter account detection benchmark,” arXiv preprint arXiv:2301.01123, 2023.
[33] N. Lozhnikov, L. Derczynski, and M. Mazzara, “Stance prediction for russian: data and analysis,” in Proceedings of 6th International Conference in Software Engineering for Defence Applications: SEDA 2018 6, pp. 176–186, Springer, 2020.
[34] 羅珮怡 and 蔣旭政, “運用 ai bert 探究臺灣新聞媒體之框架: 以 2020 年美國總統選舉議題為例,” 新聞學研究, no. 151, pp. 145–184, 2022.
[35] Y.-C. J. Lin, “Establishing legitimacy through the media and combating fake news on covid-19: a case study of taiwan,” Chinese Journal of Communication, vol. 15, no. 2, pp. 250–270, 2022.
[36] T. Niven and H.-Y. Kao, “Measuring alignment to authoritarian state media as framing bias,” in Proceedings of the 3rd NLP4IF Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda (G. Da San Martino, C. Brew, G. L. Ciampaglia, A. Feldman, C. Leberknight, and P. Nakov, eds.), (Barcelona, Spain (Online)), pp. 11–21, International Committee on Computational Linguistics (ICCL), Dec. 2020.