Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Movie Genre Classification from Plot Summaries using Bidirectional LSTM
Date
2018-02-02
Author
Ertugrul, Ali Mert
Karagöz, Pınar
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
577
views
0
downloads
Cite This
Movie plot summaries are expected to reflect the genre of movies since many spectators read the plot summaries before deciding to watch a movie. In this study, we perform movie genre classification from plot summaries of movies using bidirectional LSTM (Bi-LSTM). We first divide each plot summary of a movie into sentences and assign the genre of corresponding movie to each sentence. Next, using the word representations of sentences, we train Bi-LSTM networks. We estimate the genres for each sentence separately. Since plot summaries generally contain multiple sentences, we use majority voting for the final decision by considering the posterior probabilities of genres assigned to sentences. Our results reflect that, training Bi-LSTM network after dividing the plot summaries into their sentences and fusing the predictions for individual sentences outperform training the network with the whole plot summaries with the limited amount of data. Moreover, employing Bi-LSTM performs better compared to basic Recurrent Neural Networks (RNNs) and Logistic Regression (LR) as a baseline.
Subject Keywords
Movie genre classification
,
LSTM
,
Recurrent Neural Networks (RNNs)
URI
https://hdl.handle.net/11511/34692
DOI
https://doi.org/10.1109/icsc.2018.00043
Collections
Department of Computer Engineering, Conference / Seminar
Suggestions
OpenMETU
Core
Multi-modal dialog scene detection using hidden Markov models for content-based multimedia indexing
Alatan, Abdullah Aydın; WOLF, WAYNE (2001-06-01)
A class of audio-visual data (fiction entertainment: movies, TV series) is segmented into scenes, which contain dialogs, using a novel hidden Markov model-based (HMM) method. Each shot is classified using both audio track (via classification of speech, silence and music) and visual content (face and location information). The result of this shot-based classification is an audio-visual token to be used by the HMM state diagram to achieve scene analysis. After simulations with circular and left-to-right HMM t...
Endless pursuit realitythrough metadramatic devices in Tom Stoppard's plays Rosencrantz and Guildenstern are Dead, The Real İnspector Hound and Travesties
Yedekçi, Esra; Arslan, Yedekçi; Department of English Literature (2010)
This thesis aims to investigate the question of reality in Tom Stoppard’s plays Rosencrantz and Guildenstern are Dead, The Real Inspector Hound, and Travesties. Each of these plays closely examines the nature of reality and certainty and shows Stoppard as the critique of grand narratives of Reality, Truth, and Art. By deconstructing these master narratives, Stoppard attempts to invalidate the convictions that reality is fixed and that art should faithfully reproduce the material world in which reality is pe...
Representations of social classes in arabesk films
Avcı, Özgür; Erdoğan, Necmi; Department of Political Science and Public Administration (2004)
This thesis is an attempt to analyze the narrative structure of arabesk films which were made in the 1970s and the 1980s. Based on the idea that it is the poor/rich dichotomy which is foregrounded as the primary paradigm in arabesk films, this study tries to show how socio-cultural hierarchies are encoded in these films and how their narrative structure motivates the audience to perceive the films from a class perspective. On the basis of a generic background regarding melodramatic texts as well as a histor...
Film as a medium for unfolding the relationship between architecture and the city
Erdem, Melis; Kömez Dağlıoğlu, Esin; Güzer, Celal Abdi; Department of Architecture (2021-6)
Film and filmmaking techniques are powerful mediums that could be incorporated into the architecture and the city. Film and filmmaking techniques have long been addressed and can be traced in several discussions and ideas in architecture. With the advent of digitally-driven architecture, the integration of film into other endeavors has gained new impetus, as this technology espouses the characteristics inherent in the film. However, this discourse became more profound and evolved into layers of criticism in...
History of the novel in stories of femininity: Moll flanders, Evelina and Fordyce’s sermons /
Kaya, Tuğba Billur; Yıldız Bağçe, Hülya; Department of English Literature (2015)
In this study the rise of the English novel is investigated from the perspective of Nancy Armstrong’s Desire and Domestic Fiction which put forward that the novel genre emerged out of the conduct books of seventeenth and eighteenth centuries. Within this scope two of the first English novels Moll Flanders (1742) by Daniel Defoe and Evelina (1778) by Frances Burney will be studied side-by-side by comparing their plots with one of the most popular conduct books of the era: Fordyce’s Sermons. The study aims to...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
A. M. Ertugrul and P. Karagöz, “Movie Genre Classification from Plot Summaries using Bidirectional LSTM,” 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/34692.