<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1149">
  <Title>Entering Text with A Four-Button Device</Title>
  <Section position="8" start_page="3" end_page="3" type="evalu">
    <SectionTitle>
6 Evaluation
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="3" end_page="3" type="sub_section">
      <SectionTitle>
6.1 Number of Keystrokes
</SectionTitle>
      <Paragraph position="0"> We attached an automatic text-entry routine to TouchMeKey4 and measured the numbers of keystrokes that are needed per word. The number of keystrokes is the sum of the keystrokes required for the input and selection operations. Keystrokes for selection are counted to be n when choosing the nth-candidate.</Paragraph>
      <Paragraph position="1"> In the prediction of words, there are multiple points wherethe targetwordmaybechosen. For example, in Figure 1, the word`technology'appears asthe second-best choice after the user has typed in `41'. The user may select the target at this pointortype in another `1' to indicate the `c' and increase the target's rank. The automatic routine only chooses the target after it has appeared as the best candidate;; otherwise, the  These symbols are categorized into two groups according to the categorization used on mobile phones.</Paragraph>
      <Paragraph position="2">  routine continues to enter the word. When the full length of the word has been entered, the target word of the current ranking is chosen.</Paragraph>
      <Paragraph position="3"> Figure 2 and 3 show the relation between the amount of learning data (horizontal axis) and the number of keystrokes per word (vertical). The test document is indicated in Table 1 (7th row). Data of the same kind but from dierent positions in the test data are used for the learning data and the test data. The respective lines indicate learning when N</Paragraph>
      <Paragraph position="5"> the line. The horizontal solid line (around 5.5 taps per word) indicates the baseline, the average number of keystrokes needed to process a single word on a full keyboard. This is calculated as L avr (in Table 1)+1(for space). Note that TouchMeKey4 automatically enters the space.</Paragraph>
      <Paragraph position="6"> When there is no learning data, TouchMeKey4 needs far more keystrokes than the baseline. However, after the learning of ten thousand words, the number of keystrokes goes below the baseline when</Paragraph>
      <Paragraph position="8"> In order to see the results at macroscopic scale, Table 3 shows the results after the learning of 50 thousand words. The values indicate per-word keystrokes, and the percentages in the parentheses show the ra- null tios bywhichthenumbers of keystrokes decrease as compared with the case of no learning of a user document. We see that the numbers of keystrokes are reduced by about 30% for both ZIFF and JA. When  is around 5.5, TouchMeKey4 provides a reduction in numbers of keystrokes of almost 9 % as compared with a full keyboard. Supercially, this looks like a small gain. However, it is surprising that, even with 4 buttons, text maybeentered with fewer keystrokes than with a full keyboard.</Paragraph>
      <Paragraph position="9"> When N K = 3, on the other hand, the number of keystrokes remains at around 6.0 per word. Therefore, when N K =3, the system requires a larger number of keystrokes than the baseline.</Paragraph>
      <Paragraph position="10"> TouchMeKey4 also runs in Japanese and Thai, so we executed analogous experiments with those languages. We obtained very similar graphs in these cases. To resume, here are our observations across three languages: Learning is indispensable for systems with small</Paragraph>
      <Paragraph position="12"> values to perform better than the baseline.</Paragraph>
      <Paragraph position="13"> However, a large amount of learning data is not necessary (text with ten thousand words is enough).</Paragraph>
      <Paragraph position="14"> When N K = 3, the number of keystrokes does not fall below the baseline.</Paragraph>
    </Section>
    <Section position="2" start_page="3" end_page="3" type="sub_section">
      <SectionTitle>
6.2 Speed
</SectionTitle>
      <Paragraph position="0"> Eightsubjectswerehired totest TouchMeKey4: three in English, three in Japanese, and twoinThai.Two of the subjects for the English are nativespeakers of Japanese. The other subjects were the nativespeakers of the languages in the respective tests.</Paragraph>
      <Paragraph position="1"> The subjects were told to do 10 sessions of testing. Each session is 30 minutes long;; the subject was told to continue to enter the given text as quickly as was possible and without pausing during eachofthe sessions. The vocabulary of the given text is solely from the learned user corpus. TouchMeKey4 learned a 10-thousand-word user corpus before it was handed to the subjects. For the text entry, they were given hardware controllers that work with TouchMeKey4.</Paragraph>
      <Paragraph position="2"> Figure 4 gives the results on speed. The horizontal axis describes the sessions and the vertical axis shows the average numbers of words per minute (wpm) in each session. The respective lines indicate the speed  of the subjects over time. After 5 hours training, entry by each of the subjects was at some rate above 12 wpm. The speed of entry by the multi-tapping method on a mobile phone is in the range from 5 to 10 wpm(James and Reischel, 2001), so TouchMeKey4 obviously allows higher rates of text entry. Furthermore, the speeds are comparable to those obtained with the single-tapping method on mobile phones (7 to 25 wpm(James and Reischel, 2001)). One subject set the record, reaching 23 wpm.</Paragraph>
      <Paragraph position="3"> This speed is comparable to that of an expert with the single-tapping method. Predictive text entry thus prevented deterioration of performance, despite the number of buttons being decreased from 10 to 4.</Paragraph>
      <Paragraph position="4"> With regard to human learning, the more highly the subject was trained, the faster he or she became.</Paragraph>
      <Paragraph position="5"> The speeds of some subjects who had had diculties at the beginning of the tests had doubled by the end.</Paragraph>
      <Paragraph position="6"> Language-by-language comparison reveals that Japanese text entry was fastest. Although the entropy value for Japanese is by far greater than the values for Thai and English (4.05 for Japanese and 1.13 for Thai), the Japanese subjects managed well with TouchMeKey4 because they are accustomed to the use of predictive text entry in kana-kanji conversion. null Wemust admit that TouchMeKey4 places a heavier cognitive load on users than does text entry via a full keyboard (40 to 60 wpm) or a stylus and virtual keyboard (32.5 wpm(Zhai et al., 2000)). However, we regard the speed as satisfactory in comparison with those achieved by using single-tap-by-character entry systems on mobile phones.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>