Academia.eduAcademia.edu

Figure 1 – uploaded by Moshe Koppel

See full PDFdownloadDownload figure
FIG. 2. Ten-fold cross-validation accuracy for book attribution in 19th-century literature. Baseline (majority class) classification would give 9.6% accuracy. FIG. 1. Ten-fold cross-validation accuracy for authorship attribution in 19th-century literature. Baseline (majority class) classification would give 24% accuracy.

Figure 2 Ten-fold cross-validation accuracy for book attribution in 19th-century literature. Baseline (majority class) classification would give 9.6% accuracy. FIG. 1. Ten-fold cross-validation accuracy for authorship attribution in 19th-century literature. Baseline (majority class) classification would give 24% accuracy.

Related Figures (17)

TABLE 1. The authorship attribution corpus, comprising the chapters in a set of 20 19-century novels. The number of chapters in each book and the average number of words per chapter in each book are as shown.
TABLE 1. The authorship attribution corpus, comprising the chapters in a set of 20 19-century novels. The number of chapters in each book and the average number of words per chapter in each book are as shown.
We may tentatively examine differences between the tasks based on which functional features seemed to help the most. Examination of the features shows some clear differences among the two tasks, in terms of which sorts of features were most significant for classification, from which we can draw some tentative conclusions. Book discrimination involves a
We may tentatively examine differences between the tasks based on which functional features seemed to help the most. Examination of the features shows some clear differences among the two tasks, in terms of which sorts of features were most significant for classification, from which we can draw some tentative conclusions. Book discrimination involves a
TABLE 2. The top 20 features (by rank sum) for each of book, authorship, and nationality attribution.
TABLE 2. The top 20 features (by rank sum) for each of book, authorship, and nationality attribution.
FIG. 3. Ten-fold cross-validation accuracy for nationality attribution in 19th-century literature. Baseline (majority class) classification would give 54.0% accuracy.
FIG. 3. Ten-fold cross-validation accuracy for nationality attribution in 19th-century literature. Baseline (majority class) classification would give 54.0% accuracy.
TABLE 3. Oppositions from the 15 highest ranked systemic features for each class, with weights taken from the model learned using FW + Com + Mod for Nationality attribution.
TABLE 3. Oppositions from the 15 highest ranked systemic features for each class, with weights taken from the model learned using FW + Com + Mod for Nationality attribution.
TABLE 4. Composition of the corpus of characters’ speeches from Shakespeare. The table shows the number and average total speech length of selected characters of each gender from each play. The text has more detail on the construction of the corpus.
TABLE 4. Composition of the corpus of characters’ speeches from Shakespeare. The table shows the number and average total speech length of selected characters of each gender from each play. The text has more detail on the construction of the corpus.
FIG. 4. Accuracies for various feature sets over the corpus.
FIG. 4. Accuracies for various feature sets over the corpus.
TABLE 5. Oppositions found in the top 20 features from both genders of Shakespearean characters. Note that they are organized categorically, not in rank order.
TABLE 5. Oppositions found in the top 20 features from both genders of Shakespearean characters. Note that they are organized categorically, not in rank order.
FIG. 5. Movie review classification results for using SMO with default parameters and a linear kernel with various feature sets; see text for further details.
FIG. 5. Movie review classification results for using SMO with default parameters and a linear kernel with various feature sets; see text for further details.
TABLE 6. Top 15 features for positive and negative reviews from BoW + App, showing wo (multiplied b’ 10,000 for scaling).
TABLE 6. Top 15 features for positive and negative reviews from BoW + App, showing wo (multiplied b’ 10,000 for scaling).
FIG. 6. Ten-fold cross-validation accuracies for SMO with various feature sets, on the corpus of science articles.
FIG. 6. Ten-fold cross-validation accuracies for SMO with various feature sets, on the corpus of science articles.
TABLE7. Summary of the geology and paleontology journals used in the scientific literature corpus study, giving the number of articles from each journal in the corpus, and the average number of words per article.
TABLE7. Summary of the geology and paleontology journals used in the scientific literature corpus study, giving the number of articles from each journal in the corpus, and the average number of words per article.
TABLE 8. Oppositions from the 20 highest ranked systemic features in geology and paleontology articles, from the model learned using FW + Con + Com + Mod + App.
TABLE 8. Oppositions from the 20 highest ranked systemic features in geology and paleontology articles, from the model learned using FW + Con + Com + Mod + App.
FIG. Al. The CONJUNCTION system (Matthiessen, 1995). Options here are disjunctive; examples of lexical realizations for the leaves are given in italics. Different patterns of CONJUNCTION usage lead to markedly different textual styles. Frequent use of Extension can give a text with high information density which can give a “panoramic” effect of touring through a conceptual landscape, but if done poorly may overwhelm and lose a reader in too many facts. On the other hand, Elaboration can be used to good effect to create textual coherence around a single focused storyline. We note, too, that many of the standard function words traditionally used in computational stylistic studies are types of CONJUNCTION, which fur- ther argues for this system’s importance for stylistic text analysis.
FIG. Al. The CONJUNCTION system (Matthiessen, 1995). Options here are disjunctive; examples of lexical realizations for the leaves are given in italics. Different patterns of CONJUNCTION usage lead to markedly different textual styles. Frequent use of Extension can give a text with high information density which can give a “panoramic” effect of touring through a conceptual landscape, but if done poorly may overwhelm and lose a reader in too many facts. On the other hand, Elaboration can be used to good effect to create textual coherence around a single focused storyline. We note, too, that many of the standard function words traditionally used in computational stylistic studies are types of CONJUNCTION, which fur- ther argues for this system’s importance for stylistic text analysis.
FIG. A2. The MODALITY system networks (Matthiessen, 1995).
FIG. A2. The MODALITY system networks (Matthiessen, 1995).
FIG. A3. Examples of indicator features for various combinations of MODALITY options. Note that not all combinations are realized in the language; note also the ambiguity of some of the indicators.
FIG. A3. Examples of indicator features for various combinations of MODALITY options. Note that not all combinations are realized in the language; note also the ambiguity of some of the indicators.
FIG. A4. Options in the Attitude network, with examples of appraisal adjectives from our lexicon
FIG. A4. Options in the Attitude network, with examples of appraisal adjectives from our lexicon
Related topics:
Digital HumanitiesAuthorship AttributionSystemic Functional Linguistics
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved