1 Introduction

In this paper, we propose a chat system that uses tags to help users recall and resume past conversations.

In mediated synchronous communications such as online chat, conversational contents are often mixed because users typically discuss several topics in the same session. Users are also apt to forget what they were talking about with their online interlocutors. Therefore, it is often difficult in such scenarios to resume conversations about issues that were being discussed in the past.

Several related systems focusing on online chat or memory recall have been proposed. However, the systems proposed to date do not have functions to help users recall past conversational topics [1,2,3], or assume that users do not reread past logs to recall the contents of past chats [4]. By contrast, our system shows words associated with an ongoing chat topic onscreen to the user at any given time. The words presented are nouns extracted from chat logs by morphological analysis. Users can select multiple words as tags to represent the topic, and which help to subsequently remind them of the content of the relevant conversation.

This paper is organized as follows: in Sect. 2, we describe the related work on chat communication focusing topics. In Sect. 3, we explain our proposed system, which supports recommencement of past chat topics by tagging chat logs. A validation test for our system will be given in Sect. 4. Finally, we discuss conclusions and future work in Sect. 5.

2 Related Work on Chat Communication Focusing on Conversational Topics

Opportunities of computer mediated synchronous communication are increasing and many remote communication systems have already been proposed. One of existing typical chat services are SkypeFootnote 1 and LINEFootnote 2.

Skype allows users to register their icons, user names, and notifications indicating their statuses or moods. A chat history is shown once the user logs out. Users are also allowed to restart conversations with chat partners. LINE is a communication application that allows text and multimedia image communication. A message is shown in a balloon-shaped textbox, along with a timestamp and “message read” mark. New messages are inserted under old ones in the same window. In these services, it is possible to save each conversation as a text file. However, only the messages and their transmission times are recorded. Thus, users need all conversation logs while relying on their memory to determine where the relevant conversation was interrupted, or what they were talking about at the time.

Kawabata et al. proposed a system that extracts chat topics from a chat room using a history of messages [1]. This system presents suitable words for an ongoing conversation in a chat room in order to introduce other users, who have not yet joined the conversation, to the chat contents. In this system, a chat log saved every five minutes is divided into three parts - a “current conversation” (i.e., the conversation ongoing at the time), a last-minute conversation, and a past conversation. This system extracts nouns from each log using the Japanese morphological analyzer MeCab [5]. The log for a “current conversation” is used to obtain the characteristics of the conversation in the relevant chat room. Since last-minute topics tend to shift to a current topic, the last-minute log is analyzed to extract the characteristics of the current topic. For users who have conversed about specific subjects in the past, the system considers it likely that they will be chatting about similar issues at any given time. In order to incorporate the features of user participation in the conversation at this stage, the system extracts nouns from chat logs and gleans the conversational theme at the time. Users’ intentions are not reflected in this classification since the results of analysis in this system are only used to classify conversations into broad topics such as food, hobbies, politics, and economic. Moreover, Kawabata et al.’s system does not help remind users of past chat topics.

In all prevalent chat and instant messaging services, users can simultaneously pursue multiple topics in a conversation. At the same time, it is sometimes difficult to accurately grasp the flow of the conversation when multiple topics are being discussed, especially if several users are participating in the conversation. Collective Kairos Chat [4] is a chat support system where users can determine the degree of importance of each message. This system allows users to delete chat messages from the log at different speeds. The chat screen in the system has three columns, and messages are divided in accordance with their degree of importance as determined by all users. When chat participants have off-topic conversations, they assign the relevant messages to the column containing relatively less important messages. The log of the column containing highly important messages flows slowly, whereas the logs of the less important columns flow more quickly. As a result, important messages germane to a given theme are displayed for longer, and messages and conversations tangential to the theme are shown briefly in order for users to obtain chat logs as the collective memory of the discussion reflecting the preferences of all participants. The criterion for the importance of a message is whether it is associated with a given theme. Hence, Collective Kairos Chat does not cater to situations where multiple conversational topics are spanned in a short time.

The existing research on summarization of meeting focuses on automatic text summarization or extract of key sentences [6, 7]. In these method, the key points are presented so that user can understand the contents, the structure and the purpose of the meeting in a short time. However, users’ intentions or key phrases which users want to keep in memory are not reflected to the summarization as with Kawabata et al.’s system

In this paper, we propose a support system to facilitate checking the contents of the past issue and to restart chatting on the issue by tagging and registering topics switch timing.

3 System Framework

3.1 Design Method

Our goal is to implement a chat system that supports recommencement of past chat topics by tagging chat logs. The proposed system is designed as follows:

  1. 1.

    In order for users to continue discussion on a past chat topic, information regarding the topic is needed. However, because keeping track of all logs takes time and effort, our proposed system registers nouns from chat messages as tags.

  2. 2.

    The proposed system only presents candidate tags to users. Users can choose and freely register tags from the candidate tags presented by themselves.

3.2 System Overview

Our proposed chat system consists of a server and two clients connected to a network. Chat texts are sent to the server and the texts are stored with its sent time, the user name and the serial number in the database. In the client chat log field, only the user name and the sent texts are displayed. Each client has a candidate tag extraction function, a tag registration function, and a tag display function. Figure 1 gives an overview of the chat screen of a client.

Fig. 1.
figure 1

Overview of a client screen.

Full size image

3.3 Tag Registration Function

The tags registered by users for past chats are shown at the top of the chat window. Users click the button at the bottom of the screen to simultaneously activate the tag registration function and launch the tag extraction and registration window. The system then runs the tag extraction function and shows candidate tags to users as buttons. On clicking a candidate tag button, a message is presented indicating that the candidate has been recorded as a tag for the conversation. A list of already registered tags is also displayed on the window.

3.4 Tag Extraction Function

The tag extraction function analyzes the chat log of ongoing chats using MeCab [5], a Japanese language morphological analyzer. The log data are divided into parts of speech, and only nouns are used as candidate tags. The extracted nouns include overlapping words or words that do not make sense, such as pronouns, suffixes, and emoticons. Thus, certain nouns are selected as candidate tags.

The extracted candidate tags are displayed as a button on the window. Additionally, a user can register free words other than candidate tags as a tag. A user enters free words in the manual input form and presses the tag registration button, then the words are registered a tag. Figure 1 shows that the tags “meal invitation” and “home teacher” correspond to free words tags.

3.5 Tag Display Function

The tag display function displays the tags registered by using the tag registration function in the past chat. The proposed system displays the registered tags respectively for each chat topic or theme. Figure 2 shows the screen for selecting a theme.

The themes are displayed in a list. When a theme is selected from the pull-down menu and a display button is pushed down, tags registered with the theme in the past chat are displayed. The screen after selecting the theme is shown in the right of Fig. 2. Users can freely switch the display of themes during chat.

Fig. 2.
figure 2

A list of themes and tags registered with the selected theme.

Full size image

4 Evaluation Experiments

4.1 Experimental Overview

We performed comparison experiments to investigate whether displaying tags in our system helps users to easily recall past conversational topics.

Sixteen college students participated in our experiments. These participants were divided into eight pairs. All participants were accustomed to handling keyboard input and were familiar with chat conversations. The participants were asked to chat while sitting in the separate room in order to prevent directly conversations.

Two experiments were conducted with an interval of six days. In the first experiment, all participants used a comparison system to collect data about the last topic for the second experiment. The comparison system is only removed the tag display function from the proposed system so tags on the last topic are not displayed during the experiment using the comparison system. As there had been no registered tags in the first experiment, the participants used the comparison system.

In the second experiment, four pairs of participants used the proposed system while the other four pairs used the comparison system. The former pairs read the registered tags in the first experiment before starting the second experiment, whereas the latter pairs read all of the chat logs.

The conversations of the participants were on the following two themes: “travel” and “New Year’s party.” In the theme “travel”, the participants plan to go on a trip with several friends on a spring vacation. In the theme “New Year’s party”, the participants plan to hold a New Year’s party with classmates. Each pair chatted for ten minutes using the systems for each theme in each experiment, and registered tags during the chat. At the conclusion of the each experiment, we asked the participants to answer a few questions.

4.2 Experimental Results

The results of participants’ responses to our questionnaire are listed in Table 1. Each number signifies the total number of persons who selected that particular evaluation value.

Table 1. Questionnaire results obtained in the two experiments.
Full size table

Since the tag registration operation was identical in both systems and both themes, we conclude that differences between the systems did not affect the responses to item (ii) and the registration of tags was not troublesome for users.

From the results of item (i) and (iv), although the participants using the proposed system did not remember much of the content of the first experiment chat, they were able to chat about the theme concretely. In addition, considering the results of item (iii) and (vi), it is difficult to remember the chat content specifically in the method of remembering based on memory, it is clear that the participants were able to remember topics to a certain degree in the method of browsing the registered tags.

Comparing the results for item (v) to those for item (vi), it can be seen that the values for both systems were similar. However, it can also be seen from the results for item (vii) that participants felt that reading all of the previous chat logs was tiresome. Thus, it is possible that tags are less burdensome for users to recall previous chat contents. Additional answers optionally provided by participants also indicated that they tended to rely on the concreteness of tags.

5 Conclusion

In this article, we proposed a chat support system that helps users continue conversational topics from past chats. This system checks the contents of past conversations by tagging them based on their contents. The system applies Japanese morphological analysis to chat logs and displays nouns used in the chat as candidate tags. Users can then select and register tags that they deem helpful in remembering chat contents. Tags registered in previous chats are displayed on the upper side of the chat screen.

We performed experiments to compare our proposed system, which displays tags associated with past topics, with the comparison system that did not display registered tags. The results of comparison experiments indicate that by showing tags the proposed system helps users to virtually effortlessly recall the topics of past conversation.

In future work, we plan the following: implementation of an experiment considering the influence of order effects and theme, improvement of the interface on tag registration function and implementation of the tag delete and sorting function.